Learning Efficient Communication in Cooperative Multi-Agent Environment

By Yuhang Zhao, Xiujun Ma. 2019

4 citations recorded by the source corpus.

Reinforcement learning in cooperate multi-agent scenarios is important for real-world applications. While several attempts before tried to resolve it without explicit communication, we present a communication-filtering actor-critic algorithm that trains decentralized policies which could exchange filtered information in multi-agent settings, using centrally computed critics. Communication could potentially be an effective way for multi-agent cooperation. We supposed that, when in execution phase without central critics, high-quality communication between agents could help agents have better performance in cooperative situations. However, information sharing among all agents or in predefined communication architectures that existing methods adopt can be problematic. Therefore, we use a neural network to filter information between agents. Empirically, we show the strength of our model in two general cooperative settings and vehicle lane changing scenarios. Our approach outperforms several state-of-the-art models solving multi-agent problems.

Subfields: Artificial Intelligence, Computer Networks and Communications, Public Health, Environmental and Occupational Health, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Reinforcement Learning

Citations in the corpus

Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (2020, background): “Zhao and Ma (2019) show that the performance of decentralised policies can be improved upon through a centralised communication scheme that uses a central information-ﬁltering neural network in between timesteps.”