Reinforcement learning in a prisoner's dilemma

DOI10.1016/J.GEB.2024.01.004MaRDI QIDQ6494255

Arthur Dolgopolov

Publication date: 30 April 2024

Published in: Games and Economic Behavior (Search for Journal in Brave)

zbMATH Keywords

stochastic stabilityevolutionary game theorycollusionQ-learningpricing-algorithms

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) 2-person games (91A05) Evolutionary games (91A22)

Cites Work

• Unnamed Item
• Q-learning agents in a Cournot oligopoly model
• Evolutionary dynamics and equitable core selection in assignment games
• A one-shot deviation principle for stability in matching problems
• Evolutionary game theory: a renaissance
• Learning in extensive-form games: Experimental data and simple dynamic models in the intermediate term
• Multi-agent reinforcement learning: a selective overview of theories and algorithms
• The evolution of conventions under condition-dependent mistakes
• Rationalizability, Learning, and Equilibrium in Games with Strategic Complementarities
• 10.1162/1532443041827880
• Basins of Attraction, Long-Run Stochastic Stability, and the Speed of Step-by-Step Evolution
• Payoff-Based Dynamics for Multiplayer Weakly Acyclic Games
• The Evolution of Conventions
• A behavioral study of ``noise in coordination games

This page was built for publication: Reinforcement learning in a prisoner's dilemma