Abstract : An original Reinforcement Learning (RL) methodology is proposed for the design of multi-agent systems. In the realistic setting of situated agents with local perception, the task of automatically building a coordinated system is of crucial importance. To that end, we design simple reactive agents in a decentralized way as independent learners. But to cope with the difficulties inherent to RL used in that framework, we have developed an incremental learning algorithm where agents face a sequence of progressively more complex tasks. We illustrate this general framework by computer experiments where agents have to coordinate to reach a global goal.
https://hal.inria.fr/inria-00118983
Contributeur : Alain Dutech
<>
Soumis le : vendredi 8 décembre 2006 - 13:29:38
Dernière modification le : mardi 11 septembre 2018 - 15:18:15
Document(s) archivé(s) le : mercredi 7 avril 2010 - 00:02:12
