Almost Optimal Algorithms for Two-player Markov Games with Linear Function Approximation.

Zixiang Chen Dongruo Zhou Quanquan Gu

Published in: CoRR (2021)

Keyphrases

function approximation
reinforcement learning algorithms
function approximators
reinforcement learning
worst case
temporal difference learning algorithms
learning algorithm
temporal difference
temporal difference learning
neural network
learning tasks
incomplete information
model free