Shaping multi-agent systems with gradient reinforcement learning

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. MOTS-CLÉS : A définir par la commande ÑÓØ× Ð ×ߺºº

• Type: Journal
• Year: 2007
• Where: AAMAS
• Authors: Olivier Buffet, Alain Dutech, François Charpillet
• Keywords: AAMAS 2007, Incremental Learning Algorithm, Intelligent Agents, Original Reinforcement, Simple Reactive Agents