Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification.

Ling Pan Longbo Huang Tengyu Ma Huazhe Xu

Published in: ICML (2022)

Keyphrases

multi agent reinforcement learning
multi agent
multi agent learning
learning agents
stochastic games
reinforcement learning
multi agent systems
sufficient conditions
neural network
learning algorithm
information processing
intelligent agents
resource allocation
markov decision processes