Supported Value Regularization for Offline Reinforcement Learning.
Yixiu MaoHongchang ZhangChen ChenYi XuXiangyang JiPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- function approximation
- real time
- regularization parameter
- multi agent
- state space
- mixed norm
- blind deconvolution
- reinforcement learning algorithms
- data dependent
- markov decision processes
- transfer learning
- optimal policy
- learning process
- learning algorithm
- machine learning
- dynamical systems
- supervised learning
- active learning
- reproducing kernel hilbert space
- action space
- inverse problems
- regularization method
- stochastic approximation
- empirical risk minimization
- robotic control