A Deep Reinforcement Learning Approach For Finding Non-exploitable Strategies In Two-player Atari Games

Abstract

This paper proposes new, 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 (a) Nash-DQN algorithm, which integrates the deep learning techniques from single DQN into the classic Nash Q-learning algorithm for solving tabular Markov games; (b) Nash-DQN-Exploiter algorithm, which additionally adopts an exploiter to guide the exploration of the main agent. We conduct experimental evaluation on tabular examples as well as various two-player Atari games. Our empirical results demonstrate that (i) the policies found by many existing methods including Neural Fictitious Self Play and Policy Space Response Oracle can be prone to exploitation by adversarial opponents; (ii) the output policies of our algorithms are robust to exploitation, a

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyding2022a

Related papers

• Reinforcement Learning In Two Player Zero Sum Simultaneous Action Games (2021)0.00
• A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
• Playing Atari Games With Deep Reinforcement Learning And Human Checkpoint Replay (2016)0.00
• Efficient Competitive Self-play Policy Optimization (2020)0.00
• Efficiently Computing Nash Equilibria In Adversarial Team Markov Games (2022)0.00
• Performing Deep Recurrent Double Q-learning For Atari Games (2019)10.07
• Reward Learning From Human Preferences And Demonstrations In Atari (2018)0.00
• Neural Auto-curricula (2021)0.00