Learning Stationary Nash Equilibrium Policies in n-Player Stochastic Games with Independent Chains via Dual Mirror Descent.
S. Rasoul EtesamiPublished in: CoRR (2022)
Keyphrases
- stochastic games
- nash equilibrium
- repeated games
- nash equilibria
- multiagent reinforcement learning
- imperfect information
- markov decision processes
- game theoretic
- single agent
- learning automata
- learning algorithm
- incomplete information
- game theory
- reinforcement learning algorithms
- learning agent
- learning process
- multi agent reinforcement learning
- multi agent
- robust optimization