Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity.
Alekh AgarwalTong ZhangPublished in: CoRR (2022)
Keyphrases
- sample complexity
- sample size
- theoretical analysis
- learning algorithm
- reinforcement learning
- learning problems
- model free
- pac learning
- vc dimension
- markov chain monte carlo
- special case
- upper bound
- supervised learning
- active learning
- generalization error
- lower bound
- training examples
- sufficient conditions
- posterior distribution
- probability distribution
- random sampling
- sequential decision problems
- probabilistic model
- learning process
- learning tasks
- model selection
- training set
- computational complexity
- multi agent
- sampling algorithm
- machine learning
- concept classes
- irrelevant features
- data mining