Differentiable Arbitrating in Zero-sum Markov Games.
Jing WangMeichen SongFeng GaoBoyi LiuZhaoran WangYi WuPublished in: AAMAS (2023)
Keyphrases
- markov games
- markov decision processes
- multiagent reinforcement learning
- reinforcement learning algorithms
- markov decision process
- reinforcement learning
- control problems
- stochastic games
- state space
- multiagent systems
- nash equilibrium
- objective function
- multi agent
- cooperative
- finite state
- optimal policy
- model free
- dynamic programming
- average cost
- policy iteration
- learning algorithm
- function approximation
- finite horizon
- temporal difference learning
- adaptive control
- average reward
- game theoretic
- optimal control
- nash equilibria
- game theory