Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games.
Sihan ZengThinh T. DoanJustin RombergPublished in: NeurIPS (2022)
Keyphrases
- markov games
- markov decision processes
- multiagent reinforcement learning
- reinforcement learning algorithms
- markov decision process
- reinforcement learning
- objective function
- control problems
- cost function
- state space
- multiagent systems
- nash equilibrium
- optimal policy
- multi agent
- cooperative
- least squares
- policy iteration
- finite horizon
- temporal difference learning
- average cost
- model free
- function approximation
- optimal stopping
- random walk