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 publication36th International Conference on Machine Learning, ICML 2019
PublisherInternational Machine Learning Society (IMLS)
Pages11-20
Volume97
ISBN (Print)9781510886988
Publication statusPublished - 2019
EventInternational Conference on Machine Learning - Long Beach
Duration: 9 Jun 201915 Jun 2019
Conference number: 36

Publication series

Name36th International Conference on Machine Learning, ICML 2019
Volume2019-June

Conference

ConferenceInternational Conference on Machine Learning
Abbreviated titleICML
Period9/06/1915/06/19

ID: 51094029