Minimax-Optimal Multi-Agent RL in Zero-Sum Markov Games With a Generative Model.
Gen LiYuejie ChiYuting WeiYuxin ChenPublished in: CoRR (2022)
Keyphrases
- generative model
- markov games
- multiagent reinforcement learning
- markov decision processes
- multi agent
- reinforcement learning
- reinforcement learning algorithms
- markov decision process
- stochastic games
- control problems
- dynamic programming
- probabilistic model
- multiagent systems
- optimal stopping
- state space
- cooperative
- reward function
- optimal control
- worst case
- model free
- finite horizon
- em algorithm
- nash equilibrium
- prior knowledge
- optimal policy
- average reward
- average cost
- policy iteration
- topic models
- semi supervised
- learning algorithm
- machine learning
- partially observable
- temporal difference
- infinite horizon
- hidden variables
- function approximation
- action space
- optimal solution
- expectation maximization
- pairwise
- training data
- multi agent systems