Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium.
Qiaomin XieYudong ChenZhaoran WangZhuoran YangPublished in: COLT (2020)
Keyphrases
- function approximation
- reinforcement learning
- learning tasks
- markov games
- temporal difference learning
- learning algorithm
- stochastic games
- learning process
- multiagent reinforcement learning
- genetic algorithm
- support vector machine
- incomplete information
- model free
- reinforcement learning algorithms
- function approximators