Decentralized Q-Learning in Zero-sum Markov Games.
Muhammed O. SayinKaiqing ZhangDavid S. LeslieTamer BasarAsuman E. OzdaglarPublished in: CoRR (2021)
Keyphrases
- markov games
- multiagent reinforcement learning
- stochastic games
- multiagent systems
- multi agent
- reinforcement learning algorithms
- cooperative
- markov decision processes
- reinforcement learning
- markov decision process
- nash equilibrium
- state space
- control problems
- machine learning
- autonomous agents
- nash equilibria
- model free
- temporal difference
- average reward
- dynamic programming
- optimal stopping