Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness.
Xiaoyu WenXudong YuRui YangChenjia BaiZhen WangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- real time
- robust optimization
- partial observability
- objective function
- cost function
- computationally efficient
- image sequences
- online learning
- prior information
- online communities
- robust estimation
- markov decision processes
- online environment
- decision theory
- optimal control
- function approximation
- learning process
- machine learning
- neural network