UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning

Tarun Gupta, Anuj Mahajan, Bei Peng, Wendelin Böhmer, Shimon Whiteson

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

51 Downloads (Pure)

Abstract

VDN and QMIX are two popular value-based algorithms for cooperative MARL that learn a centralized action value function as a monotonic mixing of per-agent utilities. While this enables easy decentralization of the learned policy, the restricted joint action value function can prevent them from solving tasks that require significant coordination between agents at a given timestep. We show that this problem can be overcome by improving the joint exploration of all agents during training. Specifically, we propose a novel MARL approach called Universal Value Exploration (UneVEn) that learns a set of related tasks simultaneously with a linear decomposition of universal successor features. With the policies of already solved related tasks, the joint exploration process of all agents can be improved to help them achieve better coordination. Empirical results on a set of exploration games, challenging cooperative predator-prey tasks requiring significant coordination among agents, and StarCraft II micromanagement benchmarks show that UneVEn can solve tasks where other state-of-the-art MARL methods fail.
Original languageEnglish
Title of host publicationProceedings of the International Conference on Machine Learning (ICML)
Editors Marina Meila, Tong Zhang
Pages3930-3941
Number of pages12
Volume139
Publication statusPublished - 2021
EventInternational Conference on Machine Learning: 2021 -
Duration: 18 Jul 202124 Jul 2021
Conference number: 38th
https://icml.cc/Conferences/2021

Publication series

NameProceedings of Machine Learning Research
VolumePMLR 139
ISSN (Electronic)2640-3498

Conference

ConferenceInternational Conference on Machine Learning
Abbreviated titleICML
Period18/07/2124/07/21
Internet address

Fingerprint

Dive into the research topics of 'UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning'. Together they form a unique fingerprint.

Cite this