Shaping multi-agent systems with gradient reinforcement learning

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.

Authors

• Olivier Buffet
• Alain Dutech
• François Charpillet

Keywords

• Reinforcement learning
• Multi-agent systems
• Partially observable Markov decision processes
• Shaping
• Policy-gradient