Publication: A Novel Adaptive Weight Selection Algor...
Master data
Title: | A Novel Adaptive Weight Selection Algorithm for Multi-Objective Multi-Agent Reinforcement Learning |
Subtitle: | |
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 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 biobjective 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. |
Keywords: |
Publication type: | Article in compilation (Authorship) |
Publication date: | 2014 (Online) |
Published by: |
Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN´2014), July 6-11 2014, Beijing, China
Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN´2014), July 6-11 2014, Beijing, China
(
)
to publication |
Title of the series: | - |
Volume number: | - |
First publication: | Yes |
Version: | - |
Page: | pp. 2306 - 2314 |
Versionen
Keine Version vorhanden |
Publication date: | 2014 |
ISBN (e-book): | - |
eISSN: | - |
DOI: | http://dx.doi.org/10.1109/IJCNN.2014.6889637 |
Homepage: | https://pervasive.aau.at/publications/pdf/Vmoffaert_wcci2014.pdf |
Open access |
|
Authors
Kristof Van Moffaert (external) |
Tim Brys (external) |
Arjun Chandra (external) |
Lukas Esterle (internal) |
Peter R. Lewis (external) |
Ann Nowé (external) |
Assignment
Organisation | Address | ||||
---|---|---|---|---|---|
Fakultät für Technische Wissenschaften
Institut für Vernetzte und Eingebettete Systeme
|
AT - 9020 Klagenfurt am Wörthersee |
Categorisation
Subject areas | |
Research Cluster | No research Research Cluster selected |
Peer reviewed |
|
Publication focus |
Classification raster of the assigned organisational units:
|
working groups | No working group selected |
Cooperations
No partner organisations selected
Research activities
All related research activities to this publication are shown here. With the link below, you can view them in the search view where you are also able to export them.
Show related search activities in search
Projects: |
|
Publications: | No related publications |
Events: | No related events |
Lectures: | No related lectures |
Articles of the publication
No related publications