Bounds on sample size for policy evaluation in Markov environments
Leonid PeshkinSayan MukherjeePublished in: CoRR (2001)
Keyphrases
- variance reduction
- sample size
- policy evaluation
- upper bound
- model selection
- vc dimension
- monte carlo
- random sampling
- worst case
- confidence intervals
- markov chain
- progressive sampling
- hyperparameters
- machine learning
- data sets
- state space
- high dimensional
- generalization error
- markov decision processes
- lower bound
- reinforcement learning
- bayesian networks