Bounds on Sample Size for Policy Evaluation in Markov Environments.
Leonid PeshkinSayan MukherjeePublished in: COLT/EuroCOLT (2001)
Keyphrases
- variance reduction
- sample size
- policy evaluation
- upper bound
- random sampling
- model selection
- monte carlo
- confidence intervals
- vc dimension
- markov chain
- worst case
- least squares
- evolutionary algorithm
- hyperparameters
- objective function
- linear programming
- lower bound
- cross validation
- sample complexity
- importance sampling
- data mining