Multi-Player Zero-Sum Markov Games with Networked Separable Interactions.
Chanwoo ParkKaiqing ZhangAsuman E. OzdaglarPublished in: CoRR (2023)
Keyphrases
- markov games
- multi player
- multiagent reinforcement learning
- stochastic games
- markov decision processes
- reinforcement learning algorithms
- markov decision process
- reinforcement learning
- game playing
- control problems
- multi agent
- nash equilibrium
- nash equilibria
- online game
- multiagent systems
- state space
- cooperative
- solution concepts
- average reward
- policy iteration
- finite state
- optimal policy
- learning automata
- incomplete information
- game play
- single agent
- dynamic environments
- temporal difference
- model free
- dynamic programming