Novel single-loop policy iteration for linear zero-sum games.

Jianguo Zhao Chunyu Yang Weinan Gao Ju H. Park

Published in: Autom. (2024)

Keyphrases

policy iteration
markov decision processes
linear approximation
model free

fixed point
reinforcement learning
sample path
least squares

markov decision process
policy evaluation
temporal difference
neural network

optimal solution
optimal policy
infinite horizon
average reward