@inproceedings{0d489b42ce3c4c919bc9a6c67490405a,
title = "ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning",
abstract = "Multi-agent reinforcement learning (MARL) has achieved promising results in recent years. However, most existing reinforcement learning methods require a large amount of data for model training. In addition, data-efficient reinforcement learning requires the construction of strong inductive biases, which are ignored in the current MARL approaches. Inspired by the symmetry phenomenon in multi-agent systems, this paper proposes a framework for exploiting prior knowledge by integrating data augmentation and a well-designed consistency loss into the existing MARL methods. In addition, the proposed framework is model-agnostic and can be applied to most of the current MARL algorithms. Experimental tests on multiple challenging tasks demonstrate the effectiveness of the proposed framework. Moreover, the proposed framework is applied to a physical multi-robot testbed to show its superiority.",
author = "Xin Yu and Rongye Shi and Pu Feng and Yongkai Tian and Jie Luo and Wenjun Wu",
note = "Publisher Copyright: {\textcopyright} 2023 The Authors.; 26th European Conference on Artificial Intelligence, ECAI 2023 ; Conference date: 30-09-2023 Through 04-10-2023",
year = "2023",
month = sep,
day = "28",
doi = "10.3233/FAIA230609",
language = "英语",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press BV",
pages = "2946--2953",
editor = "Kobi Gal and Kobi Gal and Ann Nowe and Nalepa, \{Grzegorz J.\} and Roy Fairstein and Roxana Radulescu",
booktitle = "ECAI 2023 - 26th European Conference on Artificial Intelligence, including 12th Conference on Prestigious Applications of Intelligent Systems, PAIS 2023 - Proceedings",
address = "荷兰",
}