HIGHLIGHTS
- who: Reward Shaping Based Federated and collaborators from the Engineering Institute, East China Normal University, Shanghai, China have published the research: Reward Shaping Based Federated Reinforcement Learning, in the Journal: (JOURNAL)
- what: The authors propose a general reinforcement learning framework FRS which employs as the information shared among different clients with different tasks to promote each client`s training speed policy quality. In the remaining part of the paper, the authors first review previous work related to the proposed FRS framework in section II. After that, the authors evaluate FRS in Grid-World and compare . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.