Scalable and Independent Learning of Nash Equilibrium Policies in n-Player Stochastic Games with Unknown Independent Chains.
Tiancheng QinS. Rasoul EtesamiPublished in: CoRR (2023)
Keyphrases
- stochastic games
- nash equilibrium
- repeated games
- multiagent reinforcement learning
- nash equilibria
- markov decision processes
- game theory
- imperfect information
- multi agent reinforcement learning
- game theoretic
- learning automata
- learning algorithm
- multi agent
- incomplete information
- cooperative
- single agent
- reinforcement learning
- average reward
- learning process
- learning tasks
- optimal policy