10.9k citations
- Centre National de la Recherche ScientifiqueFR443 papers
- University of California, BerkeleyUS398 papers
- Lawrence Berkeley National LaboratoryUS387 papers
- Columbia UniversityUS372 papers
- Fermi National Accelerator LaboratoryUS362 papers
- University of ManchesterGB352 papers
- Sorbonne UniversitéFR348 papers
- University of MichiganUS346 papers
- University of TorontoCA345 papers
- Iowa State UniversityUS343 papers
- Université Paris CitéFR340 papers
- Michigan State UniversityUS338 papers
4 papers · 2 filters
Bellman Error Based Feature Generation using Random Projections on Sparse Spaces
Mahdi Milani Fard, Yuri Grinberg, Amir-massoud Farahmand +2
We address the problem of automatic generation of features for value function approximation. Bellman Error Basis Functions (BEBFs) have been shown to improve the error of policy ev…
Improved Estimation in Time Varying Models
Doina Precup, Philip Bachman
Locally adapted parameterizations of a model (such as locally weighted regression) are expressive but often suffer from high variance. We describe an approach for reducing the vari…
PAC-Bayesian Policy Evaluation for Reinforcement Learning
Mahdi MIlani Fard, Joelle Pineau, Csaba Szepesvari
Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, large…
Active Learning for Developing Personalized Treatment
Kun Deng, Joelle Pineau, Susan A. Murphy
The personalization of treatment via bio-markers and other risk categories has drawn increasing interest among clinical scientists. Personalized treatment strategies can be learned…