$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games.

Yuepeng Yang Cong Ma

Published in: CoRR (2022)

Keyphrases

markov games
multiagent reinforcement learning
markov decision processes
least squares
markov decision process
convergence rate
reinforcement learning algorithms
control problems
multi agent
multiagent systems
reinforcement learning
state space
finite state