5 résultats  enregistrer la recherche


...
hal-00377120v1  Communication dans un congrès
Frédéric DavesneClaude BarretInfluence of the context of a Reinforcement Learning Technique on the learning performances - A case study
Artificial Intelligence and Applications (AIA 2003), Sep 2003, Benalmádena, Spain. elec. proc., 2003
...
hal-00343201v1  Communication dans un congrès
Frédéric DavesneClaude BarretReactive Navigation of a Mobile Robot Using a Hierarchical Set of Learning Agents
Intelligent Robots and Systems conference (IROS '99), Oct 1999, Kyongju, South Korea. 1, pp.482--487, 1999, <10.1109/IROS.1999.813050>
...
hal-00343197v1  Communication dans un congrès
Frédéric DavesneLearning from Reward as an emergent property of Physics-like interactions between neurons in an artificial neural network.
European Symposium on Artificial Neural Networks (ESANN 2004), Apr 2004, Bruges, Belgium. D-Side, pp.537--542, 2004
...
hal-00377772v1  Communication dans un congrès
Frédéric DavesneClaude BarretA reactive navigation method based on an incremental learning of tasks sequences
First IEEE Workshop on Robot Motion and Control (RoMoCo 1999), Jun 1999, Kiekrz, Poland. pp.29--34, 1999, <10.1109/ROMOCO.1999.791048>