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 Contributor : Alain DutechConnect in order to contact the contributor Submitted on : Friday, December 8, 2006 - 1:29:38 PM Last modification on : Tuesday, April 5, 2022 - 3:43:45 AM Long-term archiving on: : Wednesday, April 7, 2010 - 12:02:12 AM