Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning.
Han ChaJihong ParkHyesung KimMehdi BennisSeong-Lyun KimPublished in: IEEE Intell. Syst. (2020)
Keyphrases
- reinforcement learning
- distributed systems
- multi agent
- distributed data
- distributed information systems
- cooperative
- distributed environment
- function approximation
- state space
- digital libraries
- markov decision processes
- peer to peer
- communication cost
- federated databases
- mobile agents
- fault tolerant
- action selection
- temporal difference
- distributed network
- learning problems
- learning algorithm
- communication overhead
- robotic control