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

Jacopo Castellini, Frans A. Oliehoek, Rahul Savani, Shimon Whiteson

Research output: Contribution to journalArticleScientificpeer-review

50 Downloads (Pure)

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.

Original languageEnglish
Article number25
Pages (from-to)1-53
Number of pages53
JournalAutonomous Agents and Multi-Agent Systems
Volume35
Issue number2
DOIs
Publication statusPublished - 2021

Keywords

  • Action-value representation
  • Decision-making
  • Multi-agent systems
  • Neural networks
  • One-shot games

Fingerprint

Dive into the research topics of 'Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning'. Together they form a unique fingerprint.

Cite this