Federated Offline Reinforcement Learning.
Doudou ZhouYufeng ZhangAaron Sonabend W.Zhaoran WangJunwei LuTianxi CaiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- real time
- machine learning
- markov decision processes
- digital libraries
- state space
- model free
- temporal difference
- data sources
- optimal policy
- monte carlo
- robotic control
- multi agent reinforcement learning
- reinforcement learning methods
- action selection
- direct policy search
- continuous state
- stochastic approximation
- learning capabilities
- information retrieval
- multi agent
- genetic algorithm
- learning problems
- case study
- objective function