Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability.
Aviv TamarDaniel SoudryEv ZisselmanPublished in: CoRR (2021)
Keyphrases
- generalization bounds
- algorithmic stability
- bayesian reinforcement learning
- data dependent
- learning theory
- generalization error
- optimal policy
- generalization ability
- monte carlo tree search
- uniform convergence
- vc dimension
- model selection
- statistical learning theory
- ranking algorithm
- machine learning
- reinforcement learning
- linear classifiers
- reproducing kernel hilbert space
- learning algorithm
- learning problems
- kernel machines
- ranking functions
- partially observable markov decision processes
- learning machines
- cross validation
- training set
- decision trees
- multi class