Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning.
Han ChaJihong ParkHyesung KimMehdi BennisSeong-Lyun KimPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- distributed systems
- multi agent
- federated databases
- distributed data
- distributed information systems
- distributed environment
- peer to peer
- learning algorithm
- cooperative
- lightweight
- optimal policy
- computer networks
- robotic control
- real time
- website
- function approximation
- reinforcement learning algorithms
- communication overhead
- temporal difference learning
- data sources
- machine learning