Some Aspects of Collective Reinforcement Learning for Adaptive Multi-Joined Robot
Anton Kabysh, Vladimir A. Golovko · 2011
This paper 1 describes a multi-agent influence learning approach and reinforcement learning adaptation to it. This learning technique used for distributed, adaptive and self-organizing control in multi-agent system. This technique is quite simple and uses agent’s influences to estimate learning error between them. The best influences is rewarded via reinforcement learning which is well proven learning technique. As will show, this learning rule supports positive-reward interactions between agents and does not require any additional information than standard reinforcement learning. This technique produces optimal behavior’s patterns with fast convergence.