Byzantine-Robust Online and Offline Distributed Reinforcement Learning.
Yiding ChenXuezhou ZhangKaiqing ZhangMengdi WangXiaojin ZhuPublished in: AISTATS (2023)
Keyphrases
- reinforcement learning
- fault tolerant
- multi agent
- online learning
- distributed systems
- computer networks
- model free
- cooperative
- machine learning
- real time
- databases
- robust estimation
- optimal policy
- distributed environment
- distributed network
- confidence weighted
- function approximation
- robotic control
- markov decision processes
- mobile agents
- lightweight
- peer to peer
- learning process
- search engine
- data mining