Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality
Antoine Scheid, Aymeric Capitaine, Etienne Boursier, Eric Moulines, Michael I. Jordan, Alain Durmus
摘要
In economic theory, the concept of externality refers to any indirect effect resulting from an interaction between players that affects the social welfare. Most of the models within which externality has been studied assume that agents have perfect knowledge of their environment and preferences. This is a major hindrance to the practical implementation of many proposed solutions. To address this issue, we consider a two-player bandit setting where the actions of one of the players affect the other player and we extend the Coase theorem [Coase, 1960]. This result shows that the optimal approach for maximizing the social welfare in the presence of externality is to establish property rights, i.e., enable transfers and bargaining between the players. Our work removes the classical assumption that bargainers possess perfect knowledge of the underlying game. We first demonstrate that in the absence of property rights, the social welfare breaks down. We then design a policy for the players which allows them to learn a bargaining strategy which maximizes the total welfare, recovering the Coase theorem under uncertainty.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper4
- Learning a Game by Paying the AgentsBrian Hu Zhang, Tao Lin, Yiling Chen, Tuomas SandholmICLR 2026 · 被引用 1 次
- Principal-Agent Bandit Games with Self-Interested and Exploratory Learning AgentsJunyan Liu, Lillian J. RatliffICML 2025
- Generalized Principal-Agent Problem with a Learning AgentTao Lin, Yiling ChenICLR 2025
- Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent ArrivalsJunyan Liu, Arnab Maiti, Artin Tajdini, Kevin Jamieson 等ICML 2025
它引用的顶会 Paper11
- Contracting with a Learning AgentGuru Guruganesh, Yoav Kolumbus, Jon Schneider, Inbal Talgam-Cohen 等NeurIPS 2024 · 被引用 38 次
- Online Bayesian PersuasionMatteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola GattiNeurIPS 2020 · 被引用 26 次
- Principal-Agent Reward Shaping in MDPsOmer Ben-Porat, Yishay Mansour, Michal Moshkovitz, Boaz TaitlerAAAI 2024 · 被引用 21 次
- Sequential Information Design: Learning to Persuade in the DarkMartino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti 等NeurIPS 2022 · 被引用 19 次
- Incentivized Learning in Principal-Agent Bandit GamesAntoine Scheid, Daniil Tiapkin, Etienne Boursier, Aymeric Capitaine 等ICML 2024 · 被引用 17 次
相关 Paper
- Equilibrium of Data Markets with ExternalitySafwan Hossain, Yiling ChenICML 2024 · 被引用 7 次
- LOPT: Learning Optimal Pigovian Tax in Sequential Social DilemmasYun Hua, Shang Gao, Wenhao Li, Haosheng Chen 等NeurIPS 2025 · 被引用 1 次
- Interactive Inverse Reinforcement Learning for Cooperative GamesThomas Kleine Büning, Anne-Marie George, Christos DimitrakakisICML 2022 · 被引用 7 次
- Learning to Incentivize Other Learning AgentsJiachen Yang, Ang Li, Mehrdad Farajtabar, Peter Sunehag 等NeurIPS 2020 · 被引用 105 次
- Fair Algorithms for Multi-Agent Multi-Armed BanditsSafwan Hossain, Evi Micha, Nisarg ShahNeurIPS 2021 · 被引用 69 次
