Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model.
Gen LiYuejie ChiYuting WeiYuxin ChenPublished in: NeurIPS (2022)
Keyphrases
- generative model
- multi agent
- markov games
- multiagent reinforcement learning
- reinforcement learning
- markov decision processes
- reinforcement learning algorithms
- probabilistic model
- markov decision process
- dynamic programming
- multiagent systems
- worst case
- cooperative
- state space
- optimal stopping
- model free
- hidden variables
- average cost
- finite horizon
- function approximation
- topic models
- optimal policy
- optimal solution
- em algorithm
- multi agent systems
- optimal control
- single agent
- expectation maximization
- semi supervised
- infinite horizon
- policy iteration