Individual Q-Learning in Normal Form Games

DOI10.1137/S0363012903437976zbMath1210.93085OpenAlexW1967250398MaRDI QIDQ5317140

E. J. Collins, David S. Leslie

Publication date: 15 September 2005

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/s0363012903437976

zbMATH Keywords

stochastic approximationreinforcement learningnormal form gamesmulti-agent learningplayer-dependent learning rates

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic approximation (62L20) Stochastic learning and adaptive control (93E35) Rationality and learning in game theory (91A26)

Related Items (19)

On the robustness of learning in games with stochastically perturbed payoff observations ⋮ Penalty-Regulated Dynamics and Robust Learning Procedures in Games ⋮ Reference points and learning ⋮ An adaptive learning model with foregone payoff information ⋮ Exploration-exploitation in multi-agent learning: catastrophe theory meets game theory ⋮ Fictitious Play in Zero-Sum Stochastic Games ⋮ A unified stochastic approximation framework for learning in games ⋮ Provably efficient reinforcement learning in decentralized general-sum Markov games ⋮ Independent learning in stochastic games ⋮ Learning in games with continuous action sets and unknown payoff functions ⋮ On learning dynamics underlying the evolution of learning rules ⋮ Population games and discrete optimal transport ⋮ Single-leader-multiple-follower games with boundedly rational agents ⋮ Generalised weakened fictitious play ⋮ Convergence results on stochastic adaptive learning ⋮ Learning in Games via Reinforcement and Regularization ⋮ An Adjusted Payoff-Based Procedure for Normal Form Games ⋮ An adaptive learning model in coordination games ⋮ On Gradient-Based Learning in Continuous Games

This page was built for publication: Individual Q-Learning in Normal Form Games