Publications
Contents
Cooperation, conflict, and transformative AI
Multi-agent systems
DiGiovanni, Anthony; Clifton, Jesse. Commitment games with conditional information revelation. AAAI 2023, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022, title = {Commitment games with conditional information revelation}, author = {Anthony DiGiovanni and Jesse Clifton}, url = {https://longtermrisk.org/commitment-games-with-conditional-information-revelation/, HTML https://arxiv.org/pdf/2204.03484.pdf, PDF }, year = {2022}, date = {2022-04-07}, booktitle = {AAAI 2023}, abstract = {The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games. |
DiGiovanni, Anthony; Macé, Nicolas; Clifton, Jesse. Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs. Learning, Evolution, and Games, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022b, title = {Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs}, author = {Anthony DiGiovanni and Nicolas Macé and Jesse Clifton}, url = {https://longtermrisk.org/evolutionary-stability-of-other-regarding-preferences-under-complexity-costs/, HTML https://arxiv.org/pdf/2207.03178, PDF }, year = {2022}, date = {2022-07-07}, booktitle = {Learning, Evolution, and Games}, abstract = {The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve. |
Clifton, Jesse. Collaborative game specification: arriving at common models in bargaining. Working paper, March 2021. Links | BibTeX @online{clifton-collaborative-game-2021, title = {Collaborative game specification: arriving at common models in bargaining}, author = {Jesse Clifton}, url = {https://longtermrisk.org/collaborative-game-specification/, HTML}, year = {2021}, date = {2021-03-06}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse. Weak identifiability and its consequences in strategic settings. Working paper, February 2021. Links | BibTeX @online{clifton-weak-identifiability-2021, title = {Weak identifiability and its consequences in strategic settings}, author = {Jesse Clifton}, url = {https://longtermrisk.org/weak-identifiability-and-its-consequences-in-strategic-settings/, HTML}, year = {2021}, date = {2021-02-13}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse; Riché, Maxime. Towards cooperation in learning games. Working paper, October 2020. Links | BibTeX @online{clifton-towards-cooperation-in-learning-games, title = {Towards cooperation in learning games}, author = {Jesse Clifton and Maxime Riché}, url = {https://longtermrisk.org/files/toward_cooperation_learning_games_oct_2020.pdf, PDF}, year = {2020}, date = {2020-10-01}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Oesterheld, Caspar. Robust program equilibrium. Theory and Decision, 86 (1), 2018. Links | BibTeX @article{oesterheld-robust-program-2018, title = {Robust program equilibrium}, author = {Caspar Oesterheld}, url = {https://link.springer.com/article/10.1007/s11238-018-9679-3, URL https://longtermrisk.org/files/Oesterheld2018_RobustProgramEquilibrium.pdf, PDF}, doi = {https://doi.org/10.1007/s11238-018-9679-3}, year = {2018}, date = {2018-11-01}, journal = {Theory and Decision}, volume = {86}, number = {1}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
DiGiovanni, Anthony; Clifton, Jesse. Commitment games with conditional information revelation. AAAI 2023, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022, title = {Commitment games with conditional information revelation}, author = {Anthony DiGiovanni and Jesse Clifton}, url = {https://longtermrisk.org/commitment-games-with-conditional-information-revelation/, HTML https://arxiv.org/pdf/2204.03484.pdf, PDF }, year = {2022}, date = {2022-04-07}, booktitle = {AAAI 2023}, abstract = {The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games. |
DiGiovanni, Anthony; Macé, Nicolas; Clifton, Jesse. Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs. Learning, Evolution, and Games, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022b, title = {Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs}, author = {Anthony DiGiovanni and Nicolas Macé and Jesse Clifton}, url = {https://longtermrisk.org/evolutionary-stability-of-other-regarding-preferences-under-complexity-costs/, HTML https://arxiv.org/pdf/2207.03178, PDF }, year = {2022}, date = {2022-07-07}, booktitle = {Learning, Evolution, and Games}, abstract = {The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve. |
Clifton, Jesse. Collaborative game specification: arriving at common models in bargaining. Working paper, March 2021. Links | BibTeX @online{clifton-collaborative-game-2021, title = {Collaborative game specification: arriving at common models in bargaining}, author = {Jesse Clifton}, url = {https://longtermrisk.org/collaborative-game-specification/, HTML}, year = {2021}, date = {2021-03-06}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse. Weak identifiability and its consequences in strategic settings. Working paper, February 2021. Links | BibTeX @online{clifton-weak-identifiability-2021, title = {Weak identifiability and its consequences in strategic settings}, author = {Jesse Clifton}, url = {https://longtermrisk.org/weak-identifiability-and-its-consequences-in-strategic-settings/, HTML}, year = {2021}, date = {2021-02-13}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse; Riché, Maxime. Towards cooperation in learning games. Working paper, October 2020. Links | BibTeX @online{clifton-towards-cooperation-in-learning-games, title = {Towards cooperation in learning games}, author = {Jesse Clifton and Maxime Riché}, url = {https://longtermrisk.org/files/toward_cooperation_learning_games_oct_2020.pdf, PDF}, year = {2020}, date = {2020-10-01}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Oesterheld, Caspar. Robust program equilibrium. Theory and Decision, 86 (1), 2018. Links | BibTeX @article{oesterheld-robust-program-2018, title = {Robust program equilibrium}, author = {Caspar Oesterheld}, url = {https://link.springer.com/article/10.1007/s11238-018-9679-3, URL https://longtermrisk.org/files/Oesterheld2018_RobustProgramEquilibrium.pdf, PDF}, doi = {https://doi.org/10.1007/s11238-018-9679-3}, year = {2018}, date = {2018-11-01}, journal = {Theory and Decision}, volume = {86}, number = {1}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Strategic considerations
DiGiovanni, Anthony; Clifton, Jesse. Commitment games with conditional information revelation. AAAI 2023, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022, title = {Commitment games with conditional information revelation}, author = {Anthony DiGiovanni and Jesse Clifton}, url = {https://longtermrisk.org/commitment-games-with-conditional-information-revelation/, HTML https://arxiv.org/pdf/2204.03484.pdf, PDF }, year = {2022}, date = {2022-04-07}, booktitle = {AAAI 2023}, abstract = {The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games. |
DiGiovanni, Anthony; Macé, Nicolas; Clifton, Jesse. Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs. Learning, Evolution, and Games, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022b, title = {Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs}, author = {Anthony DiGiovanni and Nicolas Macé and Jesse Clifton}, url = {https://longtermrisk.org/evolutionary-stability-of-other-regarding-preferences-under-complexity-costs/, HTML https://arxiv.org/pdf/2207.03178, PDF }, year = {2022}, date = {2022-07-07}, booktitle = {Learning, Evolution, and Games}, abstract = {The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve. |
Clifton, Jesse. Collaborative game specification: arriving at common models in bargaining. Working paper, March 2021. Links | BibTeX @online{clifton-collaborative-game-2021, title = {Collaborative game specification: arriving at common models in bargaining}, author = {Jesse Clifton}, url = {https://longtermrisk.org/collaborative-game-specification/, HTML}, year = {2021}, date = {2021-03-06}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse. Weak identifiability and its consequences in strategic settings. Working paper, February 2021. Links | BibTeX @online{clifton-weak-identifiability-2021, title = {Weak identifiability and its consequences in strategic settings}, author = {Jesse Clifton}, url = {https://longtermrisk.org/weak-identifiability-and-its-consequences-in-strategic-settings/, HTML}, year = {2021}, date = {2021-02-13}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse; Riché, Maxime. Towards cooperation in learning games. Working paper, October 2020. Links | BibTeX @online{clifton-towards-cooperation-in-learning-games, title = {Towards cooperation in learning games}, author = {Jesse Clifton and Maxime Riché}, url = {https://longtermrisk.org/files/toward_cooperation_learning_games_oct_2020.pdf, PDF}, year = {2020}, date = {2020-10-01}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Oesterheld, Caspar. Robust program equilibrium. Theory and Decision, 86 (1), 2018. Links | BibTeX @article{oesterheld-robust-program-2018, title = {Robust program equilibrium}, author = {Caspar Oesterheld}, url = {https://link.springer.com/article/10.1007/s11238-018-9679-3, URL https://longtermrisk.org/files/Oesterheld2018_RobustProgramEquilibrium.pdf, PDF}, doi = {https://doi.org/10.1007/s11238-018-9679-3}, year = {2018}, date = {2018-11-01}, journal = {Theory and Decision}, volume = {86}, number = {1}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
DiGiovanni, Anthony; Clifton, Jesse. Commitment games with conditional information revelation. AAAI 2023, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022, title = {Commitment games with conditional information revelation}, author = {Anthony DiGiovanni and Jesse Clifton}, url = {https://longtermrisk.org/commitment-games-with-conditional-information-revelation/, HTML https://arxiv.org/pdf/2204.03484.pdf, PDF }, year = {2022}, date = {2022-04-07}, booktitle = {AAAI 2023}, abstract = {The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games. |
DiGiovanni, Anthony; Macé, Nicolas; Clifton, Jesse. Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs. Learning, Evolution, and Games, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022b, title = {Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs}, author = {Anthony DiGiovanni and Nicolas Macé and Jesse Clifton}, url = {https://longtermrisk.org/evolutionary-stability-of-other-regarding-preferences-under-complexity-costs/, HTML https://arxiv.org/pdf/2207.03178, PDF }, year = {2022}, date = {2022-07-07}, booktitle = {Learning, Evolution, and Games}, abstract = {The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve. |
Clifton, Jesse. Collaborative game specification: arriving at common models in bargaining. Working paper, March 2021. Links | BibTeX @online{clifton-collaborative-game-2021, title = {Collaborative game specification: arriving at common models in bargaining}, author = {Jesse Clifton}, url = {https://longtermrisk.org/collaborative-game-specification/, HTML}, year = {2021}, date = {2021-03-06}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse. Weak identifiability and its consequences in strategic settings. Working paper, February 2021. Links | BibTeX @online{clifton-weak-identifiability-2021, title = {Weak identifiability and its consequences in strategic settings}, author = {Jesse Clifton}, url = {https://longtermrisk.org/weak-identifiability-and-its-consequences-in-strategic-settings/, HTML}, year = {2021}, date = {2021-02-13}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse; Riché, Maxime. Towards cooperation in learning games. Working paper, October 2020. Links | BibTeX @online{clifton-towards-cooperation-in-learning-games, title = {Towards cooperation in learning games}, author = {Jesse Clifton and Maxime Riché}, url = {https://longtermrisk.org/files/toward_cooperation_learning_games_oct_2020.pdf, PDF}, year = {2020}, date = {2020-10-01}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Oesterheld, Caspar. Robust program equilibrium. Theory and Decision, 86 (1), 2018. Links | BibTeX @article{oesterheld-robust-program-2018, title = {Robust program equilibrium}, author = {Caspar Oesterheld}, url = {https://link.springer.com/article/10.1007/s11238-018-9679-3, URL https://longtermrisk.org/files/Oesterheld2018_RobustProgramEquilibrium.pdf, PDF}, doi = {https://doi.org/10.1007/s11238-018-9679-3}, year = {2018}, date = {2018-11-01}, journal = {Theory and Decision}, volume = {86}, number = {1}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Decision theory
Oesterheld, Caspar. Robust program equilibrium. Theory and Decision, 86 (1), 2018. Links | BibTeX @article{oesterheld-robust-program-2018, title = {Robust program equilibrium}, author = {Caspar Oesterheld}, url = {https://link.springer.com/article/10.1007/s11238-018-9679-3, URL https://longtermrisk.org/files/Oesterheld2018_RobustProgramEquilibrium.pdf, PDF}, doi = {https://doi.org/10.1007/s11238-018-9679-3}, year = {2018}, date = {2018-11-01}, journal = {Theory and Decision}, volume = {86}, number = {1}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Malevolence
DiGiovanni, Anthony; Clifton, Jesse. Commitment games with conditional information revelation. AAAI 2023, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022, title = {Commitment games with conditional information revelation}, author = {Anthony DiGiovanni and Jesse Clifton}, url = {https://longtermrisk.org/commitment-games-with-conditional-information-revelation/, HTML https://arxiv.org/pdf/2204.03484.pdf, PDF }, year = {2022}, date = {2022-04-07}, booktitle = {AAAI 2023}, abstract = {The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games. |
DiGiovanni, Anthony; Macé, Nicolas; Clifton, Jesse. Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs. Learning, Evolution, and Games, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022b, title = {Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs}, author = {Anthony DiGiovanni and Nicolas Macé and Jesse Clifton}, url = {https://longtermrisk.org/evolutionary-stability-of-other-regarding-preferences-under-complexity-costs/, HTML https://arxiv.org/pdf/2207.03178, PDF }, year = {2022}, date = {2022-07-07}, booktitle = {Learning, Evolution, and Games}, abstract = {The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve. |
Clifton, Jesse. Collaborative game specification: arriving at common models in bargaining. Working paper, March 2021. Links | BibTeX @online{clifton-collaborative-game-2021, title = {Collaborative game specification: arriving at common models in bargaining}, author = {Jesse Clifton}, url = {https://longtermrisk.org/collaborative-game-specification/, HTML}, year = {2021}, date = {2021-03-06}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse. Weak identifiability and its consequences in strategic settings. Working paper, February 2021. Links | BibTeX @online{clifton-weak-identifiability-2021, title = {Weak identifiability and its consequences in strategic settings}, author = {Jesse Clifton}, url = {https://longtermrisk.org/weak-identifiability-and-its-consequences-in-strategic-settings/, HTML}, year = {2021}, date = {2021-02-13}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse; Riché, Maxime. Towards cooperation in learning games. Working paper, October 2020. Links | BibTeX @online{clifton-towards-cooperation-in-learning-games, title = {Towards cooperation in learning games}, author = {Jesse Clifton and Maxime Riché}, url = {https://longtermrisk.org/files/toward_cooperation_learning_games_oct_2020.pdf, PDF}, year = {2020}, date = {2020-10-01}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Oesterheld, Caspar. Robust program equilibrium. Theory and Decision, 86 (1), 2018. Links | BibTeX @article{oesterheld-robust-program-2018, title = {Robust program equilibrium}, author = {Caspar Oesterheld}, url = {https://link.springer.com/article/10.1007/s11238-018-9679-3, URL https://longtermrisk.org/files/Oesterheld2018_RobustProgramEquilibrium.pdf, PDF}, doi = {https://doi.org/10.1007/s11238-018-9679-3}, year = {2018}, date = {2018-11-01}, journal = {Theory and Decision}, volume = {86}, number = {1}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Ethics & meta-ethics
DiGiovanni, Anthony; Clifton, Jesse. Commitment games with conditional information revelation. AAAI 2023, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022, title = {Commitment games with conditional information revelation}, author = {Anthony DiGiovanni and Jesse Clifton}, url = {https://longtermrisk.org/commitment-games-with-conditional-information-revelation/, HTML https://arxiv.org/pdf/2204.03484.pdf, PDF }, year = {2022}, date = {2022-04-07}, booktitle = {AAAI 2023}, abstract = {The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games. |
DiGiovanni, Anthony; Macé, Nicolas; Clifton, Jesse. Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs. Learning, Evolution, and Games, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022b, title = {Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs}, author = {Anthony DiGiovanni and Nicolas Macé and Jesse Clifton}, url = {https://longtermrisk.org/evolutionary-stability-of-other-regarding-preferences-under-complexity-costs/, HTML https://arxiv.org/pdf/2207.03178, PDF }, year = {2022}, date = {2022-07-07}, booktitle = {Learning, Evolution, and Games}, abstract = {The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve. |
Clifton, Jesse. Collaborative game specification: arriving at common models in bargaining. Working paper, March 2021. Links | BibTeX @online{clifton-collaborative-game-2021, title = {Collaborative game specification: arriving at common models in bargaining}, author = {Jesse Clifton}, url = {https://longtermrisk.org/collaborative-game-specification/, HTML}, year = {2021}, date = {2021-03-06}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse. Weak identifiability and its consequences in strategic settings. Working paper, February 2021. Links | BibTeX @online{clifton-weak-identifiability-2021, title = {Weak identifiability and its consequences in strategic settings}, author = {Jesse Clifton}, url = {https://longtermrisk.org/weak-identifiability-and-its-consequences-in-strategic-settings/, HTML}, year = {2021}, date = {2021-02-13}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse; Riché, Maxime. Towards cooperation in learning games. Working paper, October 2020. Links | BibTeX @online{clifton-towards-cooperation-in-learning-games, title = {Towards cooperation in learning games}, author = {Jesse Clifton and Maxime Riché}, url = {https://longtermrisk.org/files/toward_cooperation_learning_games_oct_2020.pdf, PDF}, year = {2020}, date = {2020-10-01}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Oesterheld, Caspar. Robust program equilibrium. Theory and Decision, 86 (1), 2018. Links | BibTeX @article{oesterheld-robust-program-2018, title = {Robust program equilibrium}, author = {Caspar Oesterheld}, url = {https://link.springer.com/article/10.1007/s11238-018-9679-3, URL https://longtermrisk.org/files/Oesterheld2018_RobustProgramEquilibrium.pdf, PDF}, doi = {https://doi.org/10.1007/s11238-018-9679-3}, year = {2018}, date = {2018-11-01}, journal = {Theory and Decision}, volume = {86}, number = {1}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Prioritization & macrostrategy
DiGiovanni, Anthony; Clifton, Jesse. Commitment games with conditional information revelation. AAAI 2023, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022, title = {Commitment games with conditional information revelation}, author = {Anthony DiGiovanni and Jesse Clifton}, url = {https://longtermrisk.org/commitment-games-with-conditional-information-revelation/, HTML https://arxiv.org/pdf/2204.03484.pdf, PDF }, year = {2022}, date = {2022-04-07}, booktitle = {AAAI 2023}, abstract = {The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games. |
DiGiovanni, Anthony; Macé, Nicolas; Clifton, Jesse. Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs. Learning, Evolution, and Games, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022b, title = {Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs}, author = {Anthony DiGiovanni and Nicolas Macé and Jesse Clifton}, url = {https://longtermrisk.org/evolutionary-stability-of-other-regarding-preferences-under-complexity-costs/, HTML https://arxiv.org/pdf/2207.03178, PDF }, year = {2022}, date = {2022-07-07}, booktitle = {Learning, Evolution, and Games}, abstract = {The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve. |
Clifton, Jesse. Collaborative game specification: arriving at common models in bargaining. Working paper, March 2021. Links | BibTeX @online{clifton-collaborative-game-2021, title = {Collaborative game specification: arriving at common models in bargaining}, author = {Jesse Clifton}, url = {https://longtermrisk.org/collaborative-game-specification/, HTML}, year = {2021}, date = {2021-03-06}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse. Weak identifiability and its consequences in strategic settings. Working paper, February 2021. Links | BibTeX @online{clifton-weak-identifiability-2021, title = {Weak identifiability and its consequences in strategic settings}, author = {Jesse Clifton}, url = {https://longtermrisk.org/weak-identifiability-and-its-consequences-in-strategic-settings/, HTML}, year = {2021}, date = {2021-02-13}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse; Riché, Maxime. Towards cooperation in learning games. Working paper, October 2020. Links | BibTeX @online{clifton-towards-cooperation-in-learning-games, title = {Towards cooperation in learning games}, author = {Jesse Clifton and Maxime Riché}, url = {https://longtermrisk.org/files/toward_cooperation_learning_games_oct_2020.pdf, PDF}, year = {2020}, date = {2020-10-01}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Oesterheld, Caspar. Robust program equilibrium. Theory and Decision, 86 (1), 2018. Links | BibTeX @article{oesterheld-robust-program-2018, title = {Robust program equilibrium}, author = {Caspar Oesterheld}, url = {https://link.springer.com/article/10.1007/s11238-018-9679-3, URL https://longtermrisk.org/files/Oesterheld2018_RobustProgramEquilibrium.pdf, PDF}, doi = {https://doi.org/10.1007/s11238-018-9679-3}, year = {2018}, date = {2018-11-01}, journal = {Theory and Decision}, volume = {86}, number = {1}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
AI Forecasting
DiGiovanni, Anthony; Clifton, Jesse. Commitment games with conditional information revelation. AAAI 2023, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022, title = {Commitment games with conditional information revelation}, author = {Anthony DiGiovanni and Jesse Clifton}, url = {https://longtermrisk.org/commitment-games-with-conditional-information-revelation/, HTML https://arxiv.org/pdf/2204.03484.pdf, PDF }, year = {2022}, date = {2022-04-07}, booktitle = {AAAI 2023}, abstract = {The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games. |
DiGiovanni, Anthony; Macé, Nicolas; Clifton, Jesse. Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs. Learning, Evolution, and Games, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022b, title = {Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs}, author = {Anthony DiGiovanni and Nicolas Macé and Jesse Clifton}, url = {https://longtermrisk.org/evolutionary-stability-of-other-regarding-preferences-under-complexity-costs/, HTML https://arxiv.org/pdf/2207.03178, PDF }, year = {2022}, date = {2022-07-07}, booktitle = {Learning, Evolution, and Games}, abstract = {The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve. |
Clifton, Jesse. Collaborative game specification: arriving at common models in bargaining. Working paper, March 2021. Links | BibTeX @online{clifton-collaborative-game-2021, title = {Collaborative game specification: arriving at common models in bargaining}, author = {Jesse Clifton}, url = {https://longtermrisk.org/collaborative-game-specification/, HTML}, year = {2021}, date = {2021-03-06}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse. Weak identifiability and its consequences in strategic settings. Working paper, February 2021. Links | BibTeX @online{clifton-weak-identifiability-2021, title = {Weak identifiability and its consequences in strategic settings}, author = {Jesse Clifton}, url = {https://longtermrisk.org/weak-identifiability-and-its-consequences-in-strategic-settings/, HTML}, year = {2021}, date = {2021-02-13}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse; Riché, Maxime. Towards cooperation in learning games. Working paper, October 2020. Links | BibTeX @online{clifton-towards-cooperation-in-learning-games, title = {Towards cooperation in learning games}, author = {Jesse Clifton and Maxime Riché}, url = {https://longtermrisk.org/files/toward_cooperation_learning_games_oct_2020.pdf, PDF}, year = {2020}, date = {2020-10-01}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Oesterheld, Caspar. Robust program equilibrium. Theory and Decision, 86 (1), 2018. Links | BibTeX @article{oesterheld-robust-program-2018, title = {Robust program equilibrium}, author = {Caspar Oesterheld}, url = {https://link.springer.com/article/10.1007/s11238-018-9679-3, URL https://longtermrisk.org/files/Oesterheld2018_RobustProgramEquilibrium.pdf, PDF}, doi = {https://doi.org/10.1007/s11238-018-9679-3}, year = {2018}, date = {2018-11-01}, journal = {Theory and Decision}, volume = {86}, number = {1}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Other
DiGiovanni, Anthony; Clifton, Jesse. Commitment games with conditional information revelation. AAAI 2023, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022, title = {Commitment games with conditional information revelation}, author = {Anthony DiGiovanni and Jesse Clifton}, url = {https://longtermrisk.org/commitment-games-with-conditional-information-revelation/, HTML https://arxiv.org/pdf/2204.03484.pdf, PDF }, year = {2022}, date = {2022-04-07}, booktitle = {AAAI 2023}, abstract = {The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The conditional commitment abilities of mutually transparent computer agents have been studied in previous work on commitment games and program equilibrium. This literature has shown how these abilities can help resolve Prisoner's Dilemmas and other failures of cooperation in complete information settings. But inefficiencies due to private information have been neglected thus far in this literature, despite the fact that these problems are pervasive and might also be addressed by greater mutual transparency. In this work, we introduce a framework for commitment games with a new kind of conditional commitment device, which agents can use to conditionally reveal private information. We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Connecting our framework with the literature on strategic information revelation, we explore cases where conditional revelation can be used to achieve full cooperation while unconditional revelation cannot. Finally, extending previous work on program equilibrium, we develop an implementation of conditional information revelation. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games. |
DiGiovanni, Anthony; Macé, Nicolas; Clifton, Jesse. Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs. Learning, Evolution, and Games, 2022. Abstract | Links | BibTeX @conference{DiGiovanni2022b, title = {Evolutionary Stability of Other-Regarding Preferences Under Complexity Costs}, author = {Anthony DiGiovanni and Nicolas Macé and Jesse Clifton}, url = {https://longtermrisk.org/evolutionary-stability-of-other-regarding-preferences-under-complexity-costs/, HTML https://arxiv.org/pdf/2207.03178, PDF }, year = {2022}, date = {2022-07-07}, booktitle = {Learning, Evolution, and Games}, abstract = {The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve.}, howpublished = {Peer-reviewed}, keywords = {}, pubstate = {published}, tppubtype = {conference} } The evolution of preferences that account for other agents’ fitness, or other-regarding preferences, has been modeled with the “indirect approach” to evolutionary game theory. Under the indirect evolutionary approach, agents make decisions by optimizing a subjective utility function. Evolution may select for subjective preferences that differ from the fitness function, and in particular, subjective preferences for increasing or reducing other agents’ fitness. However, indirect evolutionary models typically artificially restrict the space of strategies that agents might use (assuming that agents always play a Nash equilibrium under their subjective preferences), and dropping this restriction can undermine the finding that other-regarding preferences are selected for. Can the indirect evolutionary approach still be used to explain the apparent existence of other-regarding preferences, like altruism, in humans? We argue that it can, by accounting for the costs associated with the complexity of strategies, giving (to our knowledge) the first account of the relationship between strategy complexity and the evolution of preferences. Our model formalizes the intuition that agents face tradeoffs between the cognitive costs of strategies and how well they interpolate across contexts. For a single game, these complexity costs lead to selection for a simple fixed-action strategy, but across games, when there is a sufficiently large cost to a strategy's number of context-specific parameters, a strategy of maximizing subjective (other-regarding) utility is stable again. Overall, our analysis provides a more nuanced picture of when other-regarding preferences will evolve. |
Clifton, Jesse. Collaborative game specification: arriving at common models in bargaining. Working paper, March 2021. Links | BibTeX @online{clifton-collaborative-game-2021, title = {Collaborative game specification: arriving at common models in bargaining}, author = {Jesse Clifton}, url = {https://longtermrisk.org/collaborative-game-specification/, HTML}, year = {2021}, date = {2021-03-06}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse. Weak identifiability and its consequences in strategic settings. Working paper, February 2021. Links | BibTeX @online{clifton-weak-identifiability-2021, title = {Weak identifiability and its consequences in strategic settings}, author = {Jesse Clifton}, url = {https://longtermrisk.org/weak-identifiability-and-its-consequences-in-strategic-settings/, HTML}, year = {2021}, date = {2021-02-13}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Clifton, Jesse; Riché, Maxime. Towards cooperation in learning games. Working paper, October 2020. Links | BibTeX @online{clifton-towards-cooperation-in-learning-games, title = {Towards cooperation in learning games}, author = {Jesse Clifton and Maxime Riché}, url = {https://longtermrisk.org/files/toward_cooperation_learning_games_oct_2020.pdf, PDF}, year = {2020}, date = {2020-10-01}, howpublished = {Working paper}, keywords = {}, pubstate = {published}, tppubtype = {online} } |
Oesterheld, Caspar. Robust program equilibrium. Theory and Decision, 86 (1), 2018. Links | BibTeX @article{oesterheld-robust-program-2018, title = {Robust program equilibrium}, author = {Caspar Oesterheld}, url = {https://link.springer.com/article/10.1007/s11238-018-9679-3, URL https://longtermrisk.org/files/Oesterheld2018_RobustProgramEquilibrium.pdf, PDF}, doi = {https://doi.org/10.1007/s11238-018-9679-3}, year = {2018}, date = {2018-11-01}, journal = {Theory and Decision}, volume = {86}, number = {1}, keywords = {}, pubstate = {published}, tppubtype = {article} } |