Dynamic weights in multi-objective deep reinforcement learning

Axel Abels*, Diederik M. Roijers, Tom Lenaerts, Ann Nowe, Denis Steckelmacher

*Corresponding author for this work

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review


Many real world decision problems are characterized by multiple conflicting objectives which must be balanced based on their relative importance. In the dynamic weights setting the relative importance changes over time and specialized algorithms that deal with such change, such as the tabular Reinforcement Learning (RL) algorithm by Natarajan & Tadepalli (2005), are required. However, this earlier work is not feasible for RL settings that necessitate the use of function approximators. We generalize across weight changes and high-dimensional inputs by proposing a multi-objective Q-network whose outputs are conditioned on the relative importance of objectives, and introduce Diverse Experience Replay (DER) to counter the inherent non-stationarity of the dynamic weights setting. We perform an extensive experimental evaluation and compare our methods to adapted algorithms from Deep Multi-Task/Multi-Objective RL and show that our proposed network in combination with DER dominates these adapted algorithms across weight change scenarios and problem domains.

Original languageEnglish
Title of host publicationProceedings of the 36th International Conference on Machine Learning, Long Beach, California, PMLR 97, 2019
EditorsKamalika Chaudhuri, Ruslan Salakhutdinov
PublisherInternational Machine Learning Society (IMLS)
Number of pages10
ISBN (Electronic)9781510886988
Publication statusPublished - 2019
Event36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States
Duration: 9 Jun 201915 Jun 2019

Publication series

NameProceedings of Machine Learning Research


Conference36th International Conference on Machine Learning, ICML 2019
Country/TerritoryUnited States
CityLong Beach


Dive into the research topics of 'Dynamic weights in multi-objective deep reinforcement learning'. Together they form a unique fingerprint.

Cite this