Reinforcement learning in a prisoner's dilemma

• 成果类型: Article
• 署名作者: Dolgopolov, Arthur
• 署名单位: University of Bielefeld
• 刊物名称: GAMES AND ECONOMIC BEHAVIOR
• ISSN/ISSBN: 0899-8256
• DOI: 10.1016/j.geb.2024.01.004
• 发表日期: 2024
• 页码: 84-103
• 关键词: Q-learning; stochastic stability; evolutionary game theory; collusion; Pricing-algorithms

摘要

I characterize the outcomes of a class of model -free reinforcement learning algorithms, such as stateless Q -learning, in a prisoner's dilemma. The behavior is studied in the limit as players stop experimenting after sufficiently exploring their options. A closed form relationship between the learning rate and game payoffs reveals whether the players will learn to cooperate or defect. The findings have implications for algorithmic collusion and also apply to asymmetric learners with different experimentation rules.