Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality
Antoine Scheid, Aymeric Capitaine, Etienne Boursier, Eric Moulines, Michael I. Jordan, Alain Durmus
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 2000aa92-6677-4d72-9704-94fe449c387eCited by top-tier papers4
- Learning a Game by Paying the AgentsBrian Hu Zhang, Tao Lin, Yiling Chen, Tuomas SandholmICLR 2026 · 1 citation
- 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 et al.ICML 2025
Builds on11
- Contracting with a Learning AgentGuru Guruganesh, Yoav Kolumbus, Jon Schneider, Inbal Talgam-Cohen et al.NeurIPS 2024 · 38 citations
- Online Bayesian PersuasionMatteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola GattiNeurIPS 2020 · 26 citations
- Principal-Agent Reward Shaping in MDPsOmer Ben-Porat, Yishay Mansour, Michal Moshkovitz, Boaz TaitlerAAAI 2024 · 21 citations
- Sequential Information Design: Learning to Persuade in the DarkMartino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti et al.NeurIPS 2022 · 19 citations
- Incentivized Learning in Principal-Agent Bandit GamesAntoine Scheid, Daniil Tiapkin, Etienne Boursier, Aymeric Capitaine et al.ICML 2024 · 17 citations
Related papers
- Equilibrium of Data Markets with ExternalitySafwan Hossain, Yiling ChenICML 2024 · 7 citations
- LOPT: Learning Optimal Pigovian Tax in Sequential Social DilemmasYun Hua, Shang Gao, Wenhao Li, Haosheng Chen et al.NeurIPS 2025 · 1 citation
- Interactive Inverse Reinforcement Learning for Cooperative GamesThomas Kleine Büning, Anne-Marie George, Christos DimitrakakisICML 2022 · 7 citations
- Learning to Incentivize Other Learning AgentsJiachen Yang, Ang Li, Mehrdad Farajtabar, Peter Sunehag et al.NeurIPS 2020 · 105 citations
- Fair Algorithms for Multi-Agent Multi-Armed BanditsSafwan Hossain, Evi Micha, Nisarg ShahNeurIPS 2021 · 69 citations
