Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning.
Xin ZhangZhuqing LiuJia LiuZhengyuan ZhuSongtao LuPublished in: NeurIPS (2021)
Keyphrases
- multi agent reinforcement learning
- cooperative
- distributed control
- policy evaluation
- reinforcement learning
- multi agent
- least squares
- temporal difference
- multi agent systems
- model free
- learning agents
- markov decision processes
- function approximation
- policy iteration
- multi agent learning
- stochastic games
- sample size
- game theory
- learning algorithm
- optimal policy
- variance reduction
- state space
- monte carlo
- average reward
- learning agent
- supervised learning