The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning

Castellini, Jacopo, Oliehoek, Frans A, Savani, Rahul ORCID: 0000-0003-1262-7831 and Whiteson, Shimon (2019) The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning [Website Content]

Access the full-text of this item by clicking on the Open Access link.

Abstract

Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. In this work, we empirically investigate the representational 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 quantify how well various approaches can represent the requisite value functions, and help us identify issues that can impede good performance.

Item Type:	Website Content
Uncontrolled Keywords:	46 Information and Computing Sciences, 4602 Artificial Intelligence, 4611 Machine Learning
Depositing User:	Symplectic Admin
Date Deposited:	28 May 2020 07:52
Last Modified:	23 May 2026 02:05
DOI:	10.65109/smgt4941
Open Access URL:	http://www.ifaamas.org/Proceedings/aamas2019/pdfs/...
Related Websites:	URL
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3089100
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.