Memory-two strategies forming symmetric mutual reinforcement learning equilibrium in repeated prisoners' dilemma game
Applied Mathematics and Computation Volume 444
Page 127819-
published_at 2023-03-01
Title
Memory-two strategies forming symmetric mutual reinforcement learning equilibrium in repeated prisoners' dilemma game
Abstract
We investigate symmetric equilibria of mutual reinforcement learning when both players alternately learn the optimal memory-two strategies against the oppo-nent in the repeated prisoners' dilemma game. We provide a necessary condi-tion for memory-two deterministic strategies to form symmetric equilibria. We then provide three examples of memory-two deterministic strategies which form symmetric mutual reinforcement learning equilibria. We also prove that mu-tual reinforcement learning equilibria formed by memory-two strategies are also mutual reinforcement learning equilibria when both players use reinforcement learning of memory-n strategies with n > 2.
Creators
Ueda Masahiko
[e_rad]00826571
Affiliate Master
Yamaguchi University
[kakenhi]15501
grid.268397.1
Source Identifiers
[EISSN] 0096-3003
Creator Keywords
Repeated prisoners' dilemma game
Reinforcement learning
Memory-two strategies
Languages
eng
Resource Type
journal article
Publishers
Elsevier
Date Issued
2023-03-01
Rights
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International(https://creativecommons.org/licenses/by-nc-nd/4.0/)
File Version
Accepted Manuscript
Access Rights
embargoed access
Relations
[isVersionOf]
10.1016/j.amc.2022.127819
Funding Refs
Japan Society for the Promotion of Science
[crossref_funder]https://doi.org/10.13039/501100001691
Award
Economic theory of information markets based on information science
20K19884
Funding Refs
Inamori Foundation
Award
Research topics Mathematical structure of payoff control in repeated games