zbMATH — the first resource for mathematics

Reinforcement learning approaches to coordination in cooperative multi-agent systems. (English) Zbl 1032.68692
Alonso, Eduardo (ed.) et al., Adaptive agents and multi-agent systems. Adaptation and multi-agent learning. Berlin: Springer. Lect. Notes Comput. Sci. 2636, 18-32 (2003).
Summary: We report on an investigation of reinforcement learning techniques for the learning of coordination in cooperative multi-agent systems. Specifically, we focus on two novel approaches: one is based on a new action selection strategy for Q-learning, and the other is based on model estimation with a shared action-selection protocol. The new techniques are applicable to scenarios where mutual observation of actions is not possible.
To date, reinforcement learning approaches for such independent agents did not guarantee convergence to the optimal joint action in scenarios with high miscoordination costs. We improve on previous results by demonstrating empirically that our extension causes the agents to converge almost always to the optimal joint action even in these difficult cases.
For the entire collection see [Zbl 1018.00010].

68T05 Learning and adaptive systems in artificial intelligence
Full Text: Link