Shaping Multi-Agent Systems with Gradient Reinforcement Learning

Olivier Buffet (1) , Alain Dutech (2) , François Charpillet (2)

1 LAAS - Laboratoire d'analyse et d'architecture des systèmes
2 MAIA - Autonomous intelligent machine

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: Reinforcement Learning; Multi-Agent Systems; Partially Observable Markov Decision Processes; Shaping; Policy-Gradient

Domaines: Intelligence artificielle [cs.AI]

Olivier Buffet, Alain Dutech, François Charpillet. Shaping Multi-Agent Systems with Gradient Reinforcement Learning. Autonomous Agents and Multi-Agent Systems, 2007, 15 (2), pp.197--220. ⟨10.1007/s10458-006-9010-5⟩. ⟨inria-00118983⟩