On Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks in Besov Spaces.
Thanh Nguyen-TangSunil GuptaHung Tran-TheSvetha VenkateshPublished in: Trans. Mach. Learn. Res. (2022)
Keyphrases
- sample complexity
- reinforcement learning
- learning problems
- learning algorithm
- theoretical analysis
- supervised learning
- vc dimension
- upper bound
- special case
- pac learning
- active learning
- lower bound
- sequential decision problems
- concept classes
- sample size
- training examples
- image decomposition
- generalization error
- optimal policy
- markov decision processes
- training data
- decision trees
- machine learning
- average case
- model selection
- state space
- computational complexity