Pareto-DQN: Approximating the Pareto front in complex multi-objective decision problems

Onderzoeksoutput: Conference paper

51 Downloads (Pure)

Samenvatting

In many real-world problems, one needs to care about multiple objectives. These objectives can be contradicting and, depending on the decision maker, the different compromises will be ranked differently. In this preliminary work, we propose a novel algorithm: Pareto-DQN, that will estimate the Pareto front of complex environment, with a high-dimensional state-space. As a proof-of-concept, we successfully apply our algorithm to the Deep-Sea-Treasure environment, a well known Multi-objective reinforcement learning benchmark.
Originele taal-2English
TitelProceedings of the Adaptive and Learning Agents Workshop 2019 (ALA-19) at AAMAS
Aantal pagina's6
StatusPublished - 13 mei 2019
Evenement2019 Adaptive Learning Agents (ALA) workshop: Workshop of the AAMAS conference - Montreal, Canada
Duur: 13 mei 201914 mei 2019
https://ala2019.vub.ac.be

Workshop

Workshop2019 Adaptive Learning Agents (ALA) workshop: Workshop of the AAMAS conference
Verkorte titelALA 2019
Land/RegioCanada
StadMontreal
Periode13/05/1914/05/19
Internet adres

Vingerafdruk

Duik in de onderzoeksthema's van 'Pareto-DQN: Approximating the Pareto front in complex multi-objective decision problems'. Samen vormen ze een unieke vingerafdruk.

Citeer dit