Multi-agent Policy Reciprocity with Theoretical Guarantee.
Haozhi WangYinchuan LiQing WangYunfeng ShaoJianye HaoPublished in: CoRR (2023)
Keyphrases
- theoretical guarantees
- multi agent
- policy iteration
- reinforcement learning
- optimal policy
- worst case
- cooperative
- multiple agents
- markov decision processes
- multiagent systems
- heterogeneous agents
- single agent
- machine learning
- intelligent agents
- multi agent systems
- reward function
- average cost
- markov decision process
- lower bound
- learning algorithm