Uncertainty-driven Trajectory Truncation for Model-based Offline Reinforcement Learning.
Junjie ZhangJiafei LyuXiaoteng MaJiangpeng YanJun YangLe WanXiu LiPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- model free
- data driven
- function approximation
- partial observability
- reinforcement learning algorithms
- uncertain data
- real time
- learning process
- possibility theory
- probabilistic model
- optimal policy
- monte carlo
- decision theory
- action selection
- trajectory data
- robot control
- control policy
- machine learning