Active Legibility in Multiagent Reinforcement Learning
This addresses collaboration challenges in multiagent systems for applications like autonomous driving, but it is incremental as it builds on existing legibility concepts in a new multiagent context.
The paper tackles the problem of improving collaboration in multiagent reinforcement learning by proposing an active legibility framework, where agents perform legible actions to reveal intentions and help others optimize behaviors, resulting in more efficient performance with reduced training time compared to existing algorithms.
A multiagent sequential decision problem has been seen in many critical applications including urban transportation, autonomous driving cars, military operations, etc. Its widely known solution, namely multiagent reinforcement learning, has evolved tremendously in recent years. Among them, the solution paradigm of modeling other agents attracts our interest, which is different from traditional value decomposition or communication mechanisms. It enables agents to understand and anticipate others' behaviors and facilitates their collaboration. Inspired by recent research on the legibility that allows agents to reveal their intentions through their behavior, we propose a multiagent active legibility framework to improve their performance. The legibility-oriented framework allows agents to conduct legible actions so as to help others optimise their behaviors. In addition, we design a series of problem domains that emulate a common scenario and best characterize the legibility in multiagent reinforcement learning. The experimental results demonstrate that the new framework is more efficient and costs less training time compared to several multiagent reinforcement learning algorithms.