mlsanityData to 14 Oct 2026

Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality

arXiv 2406.19824 ↗First posted 28 Jun 2024cs.GT stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 28 of its 64 references that are in the map. First posted on arXiv 28 Jun 2024.

Builds on

28 of 64 references.

References · 28

  1. 2019Introduction to Multi-Armed Banditscited by 481
  2. 2019Social Learning in Multi Agent Multi Armed Banditscited by 48
  3. 2018SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Banditscited by 47
  4. 2016Bayesian Exploration: Incentivizing Exploration in Bayesian Gamescited by 37
  5. 2022The Sample Complexity of Online Contract Designcited by 35
  6. 2017Learning to Bid Without Knowing your Valuecited by 34
  7. 2018Simple versus Optimal Contractscited by 33
  8. 2024Contracting with a Learning Agentcited by 23
  9. 2020Contracts under Moral Hazard and Adverse Selectioncited by 21
  10. 2022A survey on multi-player banditscited by 19
  11. 2022Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learningcited by 18
  12. 2023Principal-Agent Reward Shaping in MDPscited by 13
16 more
  1. 2024Incentivized Learning in Principal-Agent Bandit Gamescited by 13
  2. 2021Exploration and Incentives in Reinforcement Learningcited by 11
  3. 2022Efficient Stackelberg Strategies for Finitely Repeated Gamescited by 9
  4. 2022Sequential Information Design: Learning to Persuade in the Darkcited by 9
  5. 2023Delegating Data Collection in Decentralized Machine Learningcited by 8
  6. 2023Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Modelcited by 7
  7. 2023Repeated Principal-Agent Games with Unobserved Agent Rewards and Perfect-Knowledge Agentscited by 7
  8. 2018Bandit Learning with Positive Externalitiescited by 5
  9. 2023Estimating and Incentivizing Imperfect-Knowledge Agents with Hidden Rewardscited by 5
  10. 2024Impact of Decentralized Learning on Player Utilities in Stackelberg Gamescited by 5
  11. 2023Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgetscited by 4
  12. 2023Actions Speak What You Want: Provably Sample-Efficient Reinforcement Learning of the Quantal Stackelberg Equilibrium from Strategic Feedbackscited by 3
  13. 2023Contract Design With Safety Inspectionscited by 3
  14. 2023Robust and Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agentscited by 3
  15. 2024Learning Optimal Tax Design in Nonatomic Congestion Gamescited by 1
  16. 2024Fair Allocation in Dynamic Mechanism Designcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.