A Novel Adaptive Weight Selection Algorithm for Multi-Objective Multi-Agent Reinforcement Learning

Kristof Van Moffaert, Tim Brys, Arjun Chandra, Lukas Esterle, Peter Lewis, Ann Nowe

Research output: Chapter in Book/Report/Conference proceedingConference paperResearch

13 Citations (Scopus)

Abstract

To solve multi-objective problems, multiple reward signals are often scalarized into a single value and further processed using established single-objective problem solving techniques. While the field of multi-objective optimization has made many advances in applying scalarization techniques to obtain good solution trade-offs, the utility of applying these techniques in the multi-objective multi-agent learning domain has not yet been thoroughly investigated. Agents learn the value of their decisions by linearly scalarizing their reward signals at the local level, while acceptable system wide behaviour results. However, the non-linear relationship between weighting parameters of the algorithm and the learned policy makes the discovery of system wide trade-offs time consuming.
Our first contribution is a thorough analysis of well known scalarization schemes within the multi-objective multi-agent reinforcement learning setup. The analysed approaches intelligently explore the weight-space in order to find a wider range of system trade-offs. In our second contribution, we propose a novel adaptive weight algorithm which interacts with the underlying local multi-objective solvers and allows for a better coverage of the Pareto front. Our third contribution is the experimental validation of our approach by learning bi- objective policies in self-organising smart camera networks. We note that our algorithm (i) explores the objective space faster on many problem instances, (ii) obtained solutions that exhibit a larger hypervolume, while (iii) acquiring a greater spread in the objective space.
Original languageEnglish
Title of host publicationProceedings of the 2014 IEEE World Congress on Computational Intelligence
Place of PublicationChina
PublisherIEEE
Pages2306-2314
Number of pages8
ISBN (Print)978-1-4799-6627-1
DOIs
Publication statusPublished - 1 Jul 2014
Event2014 IEEE World Congress on Computational Intelligence (WCCI) - Beijing, China
Duration: 6 Jul 201411 Jul 2014

Conference

Conference2014 IEEE World Congress on Computational Intelligence (WCCI)
CountryChina
CityBeijing
Period6/07/1411/07/14

Keywords

  • multi-objective
  • reinforcement learning
  • scalarization
  • adaptive weights

Fingerprint Dive into the research topics of 'A Novel Adaptive Weight Selection Algorithm for Multi-Objective Multi-Agent Reinforcement Learning'. Together they form a unique fingerprint.

Cite this