A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games. (arXiv:2207.08894v2 [cs.LG] UPDATED)

This paper proposes novel, end-to-end deep reinforcement learning algorithms
for learning two-player zero-sum Markov games. Different from prior efforts on
training agents to beat a fixed set of opponents, our objective is to find the
Nash equilibrium policies that are free from exploitation by even the
adversarial opponents. We propose (1) Nash DQN algorithm, which integrates DQN
with a Nash finding subroutine for the joint value functions; and (2) Nash DQN
Exploiter algorithm, which additionally adopts an exploiter for guiding …

arxiv atari games games reinforcement reinforcement learning strategies