Multi-Agent Reinforcement Learning for Traffic Signal Control through Universal Communication Method
This addresses the problem of inefficient communication in multi-intersection traffic control for urban management, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackles the challenge of coordinating communication among intersections in multi-agent traffic signal control by proposing UniComm, a universal communication method that embeds observations into crucial predictions for neighbors, improving efficiency and universality across existing methods; experimental results show UniComm universally enhances state-of-the-art methods and UniLight significantly outperforms them in various traffic situations.
How to coordinate the communication among intersections effectively in real complex traffic scenarios with multi-intersection is challenging. Existing approaches only enable the communication in a heuristic manner without considering the content/importance of information to be shared. In this paper, we propose a universal communication form UniComm between intersections. UniComm embeds massive observations collected at one agent into crucial predictions of their impact on its neighbors, which improves the communication efficiency and is universal across existing methods. We also propose a concise network UniLight to make full use of communications enabled by UniComm. Experimental results on real datasets demonstrate that UniComm universally improves the performance of existing state-of-the-art methods, and UniLight significantly outperforms existing methods on a wide range of traffic situations.