Partial-Information Q-Learning for General Two-Player Stochastic Games.
Negash MedhinAndrew PapanicolaouMarwen ZridaPublished in: CoRR (2023)
Keyphrases
- stochastic games
- partial information
- reinforcement learning algorithms
- nash equilibria
- incomplete information
- multi agent reinforcement learning
- repeated games
- multi agent
- single agent
- state action
- reinforcement learning
- cooperative
- markov decision processes
- nash equilibrium
- state space
- average reward
- multiagent reinforcement learning
- function approximation
- optimal policy
- model free
- artificial intelligence
- temporal difference
- orders of magnitude
- learning agent
- dynamic programming
- imperfect information
- search space
- multi agent systems
- learning algorithm
- machine learning