Jeudi 7 Juillet |
09H00 | A new local search algorithm with shortlisting for plan repair in Flexible Job-Shop Problems: the 15 puzzle algorithm with potential. Helene Soubaras. |
09H30 | Une approche totalement instance pour la planification HTN. Abdeldjalil Ramoul, Damien Pellier, Humbert Fiorino and Sylvie Pesty. |
10H00 | Revisiting Goal Probability Analysis in Probabilistic Planning. Marcel Steinmetz, Joerg Hoffmann and Olivier Buffet. |
10H30 | Pause |
11H00 | Optimizing French Regions. Tristan Cazenave, Anne Epaulard and Claire Bernard. |
11H30 | Learning Macro-Actions for State-Space Planning. Sandra Castellanos-Paez, Damien Pellier, Humbert Fiorino and Sylvie Pesty. |
Déjeuner |
14H00 | Computer Go: From influence functions to AlphaGo (Tristan Cazenave) |
15H30 | Pause |
16H00 | Solving MDPs with Unknown Rewards Regardless of User Preferences. Pegah Alizadeh. |
16H20 | Intégration de recommandations simples dans un MDP. Florian Benavent and Bruno Zanuttini. |
16H40 | Analysis of Learning and Planning with Options. Ronan Fruit and Alessandro Lazaric. |
17H00 | Dealing with Markov decision process with uncertain transition functions. Martin Peron, Peter Barlette Kai Helge Becker Iadine Chades. |
19H00 | Social Event |
| |
Vendredi 8 Juillet |
09H00 | Actor-critic versus direct policy search: a comparison based on sample complexity. Arnaud de Froissard de Broissia and Olivier Sigaud. |
09H30 | Vers des architectures acteur-critique neurones efficaces en données. Matthieu Zimmer, Yann Boniface and Alain Dutch. |
10H00 | Multiple-Play Bandits Under the Position-Based Model. Paul Lagrée, Claire Vernade and Olivier Cappé. |
10H30 | Pause |
11H00 | Building document treatment chains using reinforcement learning and intuitive feedback. Esther Nicart, Bruno Zanuttini, Hugo Gilbert, Bruno Grilhères and Fredéric Praca. |
11H30 | Dora Q-Learning - making better use of explorations. Esther Nicart and Bruno Zanuttini. |
Déjeuner |
14H00 | Considering Human's Non-Deterministic Behavior and his Availability State When Designing a Collaborative Human-Robots System. Thibault Gateau, Caroline Ponzoni Carvalho Chanel, Mai-Huy Le and Frédéric Dehais. |
14H30 | LOLLIPOP: Generating and using proper plan and negative refinements for online partial order planning. Antoine Gréa, Aknine Samir and Laetitia Matignon. |
15H00 | Expert Knowledge Elicitation for "large p, small n" Regression. Marta Soare, Muhammad Ammad-Ud-Din and Samuel Kaski. |
15H20 | Fin des JFPDA |