A Generalized Minimax Q-Learning Algorithm for Two-Player Zero-Sum Stochastic Games.
Raghuram Bharadwaj DiddigiChandramouli KamanchiShalabh BhatnagarPublished in: IEEE Trans. Autom. Control. (2022)
Keyphrases
- stochastic games
- learning algorithm
- reinforcement learning algorithms
- imperfect information
- learning agent
- reinforcement learning
- nash equilibria
- markov decision processes
- multiagent reinforcement learning
- machine learning algorithms
- multi agent
- training data
- model free
- learning process
- learning automata
- average reward
- nash equilibrium
- machine learning
- game theory
- function approximation
- cooperative