Convergence rates for localized actor-critic in networked Markov potential games.

Zhaoyi Zhou Zaiwei Chen Yiheng Lin Adam Wierman

Published in: UAI (2023)

Keyphrases

convergence rate
gradient method
actor critic
step size
learning rate
approximate dynamic programming
reinforcement learning
convergence speed
temporal difference
policy iteration
policy gradient
real valued
linear programming
game theory
nash equilibria