Provable Policy Gradient Methods for Average-Reward Markov Potential Games.

Min Cheng Ruida Zhou P. R. Kumar Chao Tian

Published in: CoRR (2024)

Keyphrases

average reward
stochastic games
policy gradient
policy gradient methods
markov chain
markov decision processes
long run
optimal policy
actor critic
reinforcement learning
markov model
nash equilibria
model free
game theory
function approximation
policy iteration
gradient method