Byzantine-Robust Online and Offline Distributed Reinforcement Learning.
Yiding ChenXuezhou ZhangKaiqing ZhangMengdi WangXiaojin ZhuPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- fault tolerant
- multi agent
- real time
- distributed systems
- cooperative
- communication cost
- distributed environment
- online learning
- confidence weighted
- peer to peer
- state space
- dynamic programming
- learning process
- case study
- information systems
- learning algorithm
- optimal policy
- transfer learning
- machine learning
- computer networks
- neural network
- data sets
- database