Off-Policy Evaluation via Off-Policy Classification.
Alex IrpanKanishka RaoKonstantinos BousmalisChris HarrisJulian IbarzSergey LevinePublished in: CoRR (2019)
Keyphrases
- policy evaluation
- classification accuracy
- least squares
- text classification
- support vector machine svm
- decision trees
- feature vectors
- support vector machine
- supervised learning
- learning algorithm
- reinforcement learning
- training set
- machine learning algorithms
- temporal difference
- machine learning
- objective function
- neural network