Nash Q-Learning for General-Sum Stochastic Games.
Junling HuMichael P. WellmanPublished in: J. Mach. Learn. Res. (2003)
Keyphrases
- reinforcement learning
- cooperative
- function approximation
- multi agent
- state space
- stochastic approximation
- nash equilibrium
- reinforcement learning algorithms
- game theory
- learning algorithm
- action selection
- multi agent reinforcement learning
- optimal policy
- utility function
- learning rate
- model free
- nash equilibria
- state action
- temporal difference learning
- potential field
- dynamic programming
- temporal difference
- sufficient conditions
- stochastic games
- reinforcement learning methods
- td learning
- machine learning
- stochastic shortest path
- social welfare
- least squares
- genetic algorithm