Reinforcement learning 2
Session details
Reinforcement learning 2
Thursday 10 September
16:00 - 17:40
Location: Room Preseren - Hotel Park
| 16:00 | Efficient Sample Reuse in EM-based Policy Search (Hirotaka Hachiya, Jan Peters, Masashi Sugiyama) |
| 16:25 | Learning the difference between partially observable dynamical systems (Sami Zhioua, Josee Desharnais, Francois Laviolette, Doina Precup) |
| 16:50 | Optimal Online Learning Procedures for Model-Free Policy Evaluation (Tsuyoshi Ueno, Shin-ichi Maeda, Motoaki Kawanabe, Shin Ishii) |
| 17:15 | Boosting Active Learning to Optimality: a Tracable Monte-Carlo, Billiard-based Algorithm (Philippe Rolet, Michèle Sebag, Olivier Teytaud) |