Policy Evaluation and Seeking for Multi-Agent Reinforcement Learning via Best Response.
Rui YanXiaoming DuanZongying ShiYisheng ZhongJason R. MardenFrancesco BulloPublished in: CoRR (2020)
Keyphrases
- multi agent reinforcement learning
- policy evaluation
- reinforcement learning
- least squares
- temporal difference
- model free
- monte carlo
- markov decision processes
- function approximation
- multi agent
- policy iteration
- variance reduction
- stochastic games
- learning agents
- multi agent learning
- semi parametric
- cooperative
- state space
- multi agent systems
- machine learning
- partially observable
- supervised learning
- distributed control