Offline Reinforcement Learning with Adaptive Behavior Regularization.
Yunfan ZhouXijun LiQingyu QuPublished in: CoRR (2022)
Keyphrases
- adaptive behavior
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- state space
- real time
- markov decision processes
- optimal policy
- supervised learning
- machine learning
- prior information
- temporal difference
- learning process
- model free
- adaptive control
- computer vision
- learning capabilities
- transfer learning
- fuzzy logic
- regularization parameter