Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning

Shariq Iqbal, Christian A. Schroeder de Witt, Bei Peng, Wendelin Böhmer, Shimon Whiteson, Fei Sha

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

3 Downloads (Pure)

Abstract

Real world multi-agent tasks often involve varying types and quantities of agents and non-agent entities; however, agents within these tasks rarely need to consider all others at all times in order to act effectively. Factored value function approaches have historically leveraged such independences to improve learning efficiency, but these approaches typically rely on domain knowledge to select fixed subsets of state features to include in each factor. We propose to utilize value function factoring with random subsets of entities in each factor as an auxiliary objective in order to disentangle value predictions from irrelevant entities. This factoring approach is instantiated through a simple attention mechanism masking procedure. We hypothesize that such an approach helps agents learn more effectively in multi-agent settings by discovering common trajectories across episodes within sub-groups of agents/entities. Our approach, Randomized Entity-wise Factorization for Imagined Learning (REFIL), outperforms all strong baselines by a significant margin in challenging StarCraft micromanagement tasks.
Original languageEnglish
Title of host publicationProceedings of the 37th International Conference on Machine Learning, ICML 2020
EditorsMarina Meila, Tong Zhang
Pages4596-4606
Number of pages11
Volume139
Publication statusPublished - 2021
EventInternational Conference on Machine Learning: 2021 -
Duration: 18 Jul 202124 Jul 2021
Conference number: 38th
https://icml.cc/Conferences/2021

Conference

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

Fingerprint

Dive into the research topics of 'Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning'. Together they form a unique fingerprint.

Cite this