A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games.
Zihan DingDijia SuQinghua LiuChi JinPublished in: CoRR (2022)
Keyphrases
- learning agents
- reinforcement learning
- repeated games
- linear value function approximation
- reinforcement learning algorithms
- nash equilibria
- perfect information
- nash equilibrium
- game theoretic
- imperfect information
- function approximation
- optimal strategy
- multi agent
- stochastic games
- solution concepts
- learning agent
- game playing
- learning process
- multiagent systems
- state space
- learning algorithm
- markov games
- equilibrium strategies
- optimal policy
- control problems
- markov decision processes
- machine learning
- computer games
- average reward
- temporal difference
- optimal control