Aarhus University Seal / Aarhus Universitets segl

Lukas Esterle

A novel adaptive weight selection algorithm for multi-objective multi-agent reinforcement learning

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisKonferenceartikelForskningpeer review


  • Kristof Van Moffaert, Vrije Universiteit Brussel
  • ,
  • Tim Brys, Vrije Universiteit Brussel
  • ,
  • Arjun Chandra, Universitetet i Oslo
  • ,
  • Lukas Esterle
  • Peter R. Lewis, Aston University
  • ,
  • Ann Nowe, Vrije Universiteit Brussel

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 scalarization function 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.

TidsskriftProceedings of the International Joint Conference on Neural Networks
Sider (fra-til)2306-2314
Antal sider9
StatusUdgivet - 3 sep. 2014
Eksternt udgivetJa
Begivenhed2014 International Joint Conference on Neural Networks, IJCNN 2014 - Beijing, Kina
Varighed: 6 jul. 201411 jul. 2014


Konference2014 International Joint Conference on Neural Networks, IJCNN 2014

Se relationer på Aarhus Universitet Citationsformater

ID: 170584526