Symmetric equilibrium of multi-agent reinforcement learning in repeated prisoner's dilemma

DOI10.1016/j.amc.2021.126370OpenAlexW3123542883MaRDI QIDQ2244146

Masahiko Ueda, Yuki Usui

Publication date: 11 November 2021

Published in: Applied Mathematics and Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2101.11861

zbMATH Keywords

reinforcement learningrepeated prisoner's dilemma game

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Game theory (91Axx) Genetics and population dynamics (92Dxx) Applications of dynamical systems (37Nxx) Computer science (68-XX)

Related Items (4)

Replicator dynamics of the hawk-dove game with different stochastic noises in infinite populations ⋮ Analysis of dynamic evolution process of the N-player division of labor game model ⋮ Memory-two strategies forming symmetric mutual reinforcement learning equilibrium in repeated prisoners' dilemma game ⋮ Controlling conditional expectations by zero-determinant strategies

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Tit-for-tat or win-stay, lose-shift?
• The Iterated Prisoner's Dilemma: Good Strategies and Their Dynamics
• The Evolution of Cooperation
• Chaos in learning a simple two-person game
• 10.1162/1532443041827880
• Complex dynamics in learning complicated games
• The Logic of Animal Conflict
• Optimal policies for the Prisoner's Dilemma.

This page was built for publication: Symmetric equilibrium of multi-agent reinforcement learning in repeated prisoner's dilemma