MSRL: Distributed Reinforcement Learning with Dataflow Fragments.
Huanzhou ZhuBo ZhaoGang ChenWeifeng ChenYijie ChenLiang ShiYaodong YangPeter R. PietzuchLei ChenPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- multi agent
- communication overhead
- distributed systems
- markov decision processes
- temporal difference
- parallel computing
- data flow
- function approximation
- computing environments
- computer networks
- optimal policy
- peer to peer
- learning process
- mobile agents
- database
- distributed environment
- lightweight
- fault tolerant
- supervised learning
- design methodology
- cooperative
- distributed data
- model free
- learning algorithm
- reinforcement learning algorithms
- data sets