Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning

Castellini, Jacopo, Oliehoek, Frans A ORCID: 0000-0003-4372-5055, Savani, Rahul ORCID: 0000-0003-1262-7831 and Whiteson, Shimon (2021) Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning. AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, 35 (2). 25-.

Text
Castellini2021_Article_AnalysingFactorizationsOfActio.pdf - Published version
Download (3MB) | Preview

Official URL: http://dx.doi.org/10.1007/s10458-021-09506-w

Abstract

Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are learning, or how we should enhance their learning power to address the problems on which they fail. In this work, we empirically investigate the learning power of various network architectures on a series of one-shot games. Despite their simplicity, these games capture many of the crucial problems that arise in the multi-agent setting, such as an exponential number of joint actions or the lack of an explicit coordination mechanism. Our results extend those in Castellini et al. (Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS'19.International Foundation for Autonomous Agents and Multiagent Systems, pp 1862-1864, 2019) and quantify how well various approaches can represent the requisite value functions, and help us identify the reasons that can impede good performance, like sparsity of the values or too tight coordination requirements.

Item Type:	Article
Uncontrolled Keywords:	Multi-agent systems, Neural networks, Decision-making, Action-value representation, One-shot games
Divisions:	Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	21 Jun 2021 07:57
Last Modified:	18 Jan 2023 22:34
DOI:	10.1007/s10458-021-09506-w
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3126938