Nowadays, development of adaptive multi-agentsystems has attracted recent attention. Adaptive systems arecapable of adapting themselves to unforeseen changes oftheir environment in autonomous manner. We areinterested, in this paper, to adaptation in cooperativesystems where agents share a same goal. We propose anadaptive approach based on interaction evaluation andgenetic algorithms. Agents, in this approach, have the abilityto reorganize themselves in order to bring closer agentscapable of cooperating in problem solving. The adaptationtask is accomplished at both local and global levels. Wepresent here details of this approach and we show somepreliminary experimentation results.
展开▼
