| Learning exploration/exploitation strategies for single trajectory reinforcement learning M Castronovo, F Maes, R Fonteneau, D Ernst European Workshop on Reinforcement Learning, 1-10, 2013 | 41 | 2013 |
| Benchmarking for bayesian reinforcement learning M Castronovo, D Ernst, A Couëtoux, R Fonteneau PloS one 11 (6), e0157088, 2016 | 13 | 2016 |
| Bayes Adaptive Reinforcement Learning versus Off-line Prior-based Policy Search: an Empirical Comparison M Castronovo, D Ernst, R Fonteneau Proceedings of the 23rd annual machine learning conference of Belgium and …, 2014 | 3 | 2014 |
| Approximate Bayes Optimal Policy Search using Neural Networks M Castronovo, V François-Lavet, R Fonteneau, D Ernst, A Couëtoux Proceedings of the 9th International Conference on Agents and Artificial …, 2017 | 2 | 2017 |
| Offline Policy-search in Bayesian Reinforcement Learning M Castronovo Université de Liège, Liège, Belgique, 2017 | 1 | 2017 |
| Apprentissage par renforcement bayésien versus recherche directe de politique hors-ligne en utilisant une distribution a priori: comparaison empirique M Castronovo, D Ernst, R Fonteneau Proceedings des 9èmes Journée Francophones de Planification, Décision et …, 2014 | | 2014 |
| Learning for exploration/exploitation in reinforcement learning C Michael | | 2012 |
| Learning for exploration/exploitation in reinforcement learning M Castronovo Université de Liège, Liège, Belgique, 2012 | | 2012 |
Damien ErnstProfessor at the University of Liège and co-founder of Blacklight AnalyticsVerified email at ulg.ac.be
