This paper presents a learning mechanism allowing a multi-agent system to cooperate to achieve a gathering task efficiently in unknown and changing environments. The multi-agent system is a team of autonomous behaviour-based agents with limited communication capabilities. Cooperation is based on the acquisition of signaling behaviours and on the specialization of the agents into different types. Every agent has the same collection of built-in-reactive behaviours. Some of the built-in behaviours are fixed, while others can be modified through reinforcement learning. The reinforcement signal is delayed until the completion of a trial and assesses the collective performance of the team. Each agent uses this common signal to learn what individual behaviours are more suitable for the team. Simulation results, and the corresponding statisticla analysis, show that the multi-agent system always achieves near-to-optimal performances. ; JRC.(ISIS)-Institute For Systems, Informatics And Safety
Learning Signaling Behaviors and Specialization in Cooperative Agents
06.08.1996
Sonstige
Elektronische Ressource
Englisch
Learning Collective Crowd Behaviors with Dynamic Pedestrian-Agents
British Library Online Contents | 2015
|British Library Online Contents | 1997
|Sogerma: Greater specialization
Online Contents | 1997
|Engineering Index Backfile | 1933
|Cooperative Learning Hybrid Agents for Traffic Management and Control
British Library Conference Proceedings | 2002
|