Reinforcement Learning 2
Thursday 18 September
14:00 - 15:20
Location: R001
Session chair: Shimon Whiteson
| 14:00 | State-Dependent Exploration for Policy Gradient Methods
Thomas Rückstiess, Martin Felder, Jürgen Schmidhuber
View abstract |
| 14:20 | A New Natural Policy Gradient by Stationary Distribution Metric
Tetsuro Morimura, Eiji Uchibe, Junichiro Yoshimoto, Kenji Doya
View abstract |
| 14:40 | Fitted Natural Actor-Critic: A New Algorithm for Continuous State-Action MDPs
Francisco S. Melo, Manuel C. Lopes
View abstract |
| 15:00 | Learning MDP Action Models via Discrete Mixture Trees
Michael Wynkoop, Thomas Dietterich
View abstract |
