Two-Timescale Q-Learning with Function Approximation in Zero-Sum Stochastic Games.
Zaiwei ChenKaiqing ZhangEric MazumdarAsuman E. OzdaglarAdam WiermanPublished in: CoRR (2023)
Keyphrases
- stochastic games
- function approximation
- reinforcement learning algorithms
- reinforcement learning
- model free
- temporal difference
- markov decision processes
- temporal difference learning
- average reward
- multiagent reinforcement learning
- nash equilibria
- multi agent
- function approximators
- state action
- learning agent
- learning automata
- td learning
- nash equilibrium
- radial basis function
- single agent
- repeated games
- state space
- robust optimization
- genetic algorithm
- active learning
- neural network
- policy iteration
- dynamic environments
- temporal difference methods