K-Nearest-Neighbor Resampling for Off-Policy Evaluation in Stochastic Control.
Michael GiegrichRoel OomenChristoph ReisingerPublished in: CoRR (2023)
Keyphrases
- k nearest neighbor
- knn
- temporal difference
- nearest neighbor
- policy iteration
- least squares
- model free
- support vector machine
- reinforcement learning
- control problems
- optimal control
- function approximation
- neural network
- markov decision processes
- text categorization
- reinforcement learning algorithms
- support vector machine svm
- input space
- text classification
- monte carlo
- fixed point
- markov chain