Decentralized Q-learning in Zero-sum Markov Games.
Muhammed O. SayinKaiqing ZhangDavid S. LeslieTamer BasarAsuman E. OzdaglarPublished in: NeurIPS (2021)
Keyphrases
- markov games
- multiagent reinforcement learning
- stochastic games
- reinforcement learning algorithms
- multi agent
- multiagent systems
- markov decision processes
- cooperative
- reinforcement learning
- markov decision process
- state space
- control problems
- dynamic programming
- supervised learning
- random walk
- nash equilibrium
- nash equilibria