Work

Active legibility in multiagent reinforcement learning

Year: 2025

Type: article

Abstract: 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 drives 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 legibility-needed scenario and effectively characterize the legibility in multiagent reinforcement learning. The experimental results demonstrate that the new framework is more efficient and requires less training time compared to several multiagent reinforcement learning algorithms.

Source: Artificial Intelligence

DOI: 10.1016/j.artint.2025.104357

Authors: Yanyu Liu, Yinghui Pan, Yifeng Zeng, Biyang Ma, Prashant Doshi

Institutions: Central South University, Shenzhen University, Northumbria University, Minnan Normal University

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $4,260

Funders: National Natural Science Foundation of China, Natural Science Foundation of Fujian Province, Natural Science Foundation of Guangdong Province, Shenzhen University