Distributed Offline Reinforcement Learning.
Paulo HerediaJemin GeorgeShaoshuai MouPublished in: CDC (2022)
Keyphrases
- reinforcement learning
- multi agent
- distributed systems
- function approximation
- optimal policy
- distributed learning
- database
- distributed architecture
- reinforcement learning algorithms
- fault tolerant
- computer networks
- distributed environment
- lightweight
- genetic algorithm
- machine learning
- neural network
- real time
- supervised learning
- markov decision processes
- state space
- dynamic programming
- communication overhead
- data sets