Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance.
Qisen YangShenzhi WangQihang ZhangGao HuangShiji SongPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- tens of thousands
- real time
- machine learning
- domain experts
- adaptive control
- robot control
- function approximation
- state space
- human experts
- databases
- expert knowledge
- adaptive filtering
- multi agent
- decision making
- neural network
- temporal difference learning
- learning capabilities
- temporal difference
- optimal control
- learning problems
- optimal policy
- data driven