REINFORCEMENT LEARNING IN MARKOVIAN EVOLUTIONARY GAMES

DOI10.1142/S0219525902000535zbMath1053.91022OpenAlexW1964886424WikidataQ127770019 ScholiaQ127770019MaRDI QIDQ4425274

Vivek S. Borkar

Publication date: 2002

Published in: Advances in Complex Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s0219525902000535

zbMATH Keywords

generalized Nash equilibriaexpectation formationstochastic dynamic gamesactor-critic methods

Mathematics Subject Classification ID

Evolutionary games (91A22)

Related Items (6)

Reinforcement learning explains various conditional cooperation ⋮ Fictitious Play in Zero-Sum Stochastic Games ⋮ Independent learning in stochastic games ⋮ Dynamics of Bayesian updating with dependent data and misspecified models ⋮ Best-response dynamics in zero-sum stochastic games ⋮ Convergent multiple-timescales reinforcement learning algorithms in normal form games

Cites Work

• Statistical solutions of differential equations with non-uniquely solvable Cauchy problems
• Conjectural equilibrium in multiagent learning
• Elevator group control using multiple reinforcement learning agents
• Learning mixed equilibria
• Learning through reinforcement and replicator dynamics
• Stochastic approximation with two time scales
• Ergodic properties of weak asymptotic pseudotrajectories for semiflows
• Mixed equilibria and dynamical systems arising from fictitious play in perturbed games
• On N-person stochastic games by denumerable state space
• OPTIMAL PAYOFF FUNCTIONS FOR MEMBERS OF COLLECTIVES
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• A Stochastic Approximation Method

This page was built for publication: REINFORCEMENT LEARNING IN MARKOVIAN EVOLUTIONARY GAMES