Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950596486> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2950596486 abstract "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 a tabular Reinforcement Learning (RL) algorithm by Natarajan and 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 we 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 Reinforcement Learning and show that our proposed network in combination with DER dominates these adapted algorithms across weight change scenarios and problem domains." @default.
- W2950596486 created "2019-06-27" @default.
- W2950596486 creator A5003581663 @default.
- W2950596486 creator A5064553018 @default.
- W2950596486 creator A5067283098 @default.
- W2950596486 creator A5081436755 @default.
- W2950596486 creator A5085949536 @default.
- W2950596486 date "2018-09-20" @default.
- W2950596486 modified "2023-09-23" @default.
- W2950596486 title "Dynamic Weights in Multi-Objective Deep Reinforcement Learning." @default.
- W2950596486 cites W1757796397 @default.
- W2950596486 cites W1987725948 @default.
- W2950596486 cites W1998649829 @default.
- W2950596486 cites W2012612381 @default.
- W2950596486 cites W2097381042 @default.
- W2950596486 cites W2121863487 @default.
- W2950596486 cites W2126105956 @default.
- W2950596486 cites W2147750403 @default.
- W2950596486 cites W2155968351 @default.
- W2950596486 cites W2173564293 @default.
- W2950596486 cites W2174786457 @default.
- W2950596486 cites W2185917628 @default.
- W2950596486 cites W2530195778 @default.
- W2950596486 cites W2558738305 @default.
- W2950596486 cites W2606733399 @default.
- W2950596486 cites W2892979040 @default.
- W2950596486 cites W2962717849 @default.
- W2950596486 cites W2962985403 @default.
- W2950596486 cites W2963584407 @default.
- W2950596486 cites W2964048876 @default.
- W2950596486 cites W3011120880 @default.
- W2950596486 hasPublicationYear "2018" @default.
- W2950596486 type Work @default.
- W2950596486 sameAs 2950596486 @default.
- W2950596486 citedByCount "1" @default.
- W2950596486 countsByYear W29505964862020 @default.
- W2950596486 crossrefType "posted-content" @default.
- W2950596486 hasAuthorship W2950596486A5003581663 @default.
- W2950596486 hasAuthorship W2950596486A5064553018 @default.
- W2950596486 hasAuthorship W2950596486A5067283098 @default.
- W2950596486 hasAuthorship W2950596486A5081436755 @default.
- W2950596486 hasAuthorship W2950596486A5085949536 @default.
- W2950596486 hasConcept C119857082 @default.
- W2950596486 hasConcept C126255220 @default.
- W2950596486 hasConcept C14036430 @default.
- W2950596486 hasConcept C154945302 @default.
- W2950596486 hasConcept C162324750 @default.
- W2950596486 hasConcept C187736073 @default.
- W2950596486 hasConcept C2780451532 @default.
- W2950596486 hasConcept C33923547 @default.
- W2950596486 hasConcept C41008148 @default.
- W2950596486 hasConcept C78458016 @default.
- W2950596486 hasConcept C86803240 @default.
- W2950596486 hasConcept C97541855 @default.
- W2950596486 hasConceptScore W2950596486C119857082 @default.
- W2950596486 hasConceptScore W2950596486C126255220 @default.
- W2950596486 hasConceptScore W2950596486C14036430 @default.
- W2950596486 hasConceptScore W2950596486C154945302 @default.
- W2950596486 hasConceptScore W2950596486C162324750 @default.
- W2950596486 hasConceptScore W2950596486C187736073 @default.
- W2950596486 hasConceptScore W2950596486C2780451532 @default.
- W2950596486 hasConceptScore W2950596486C33923547 @default.
- W2950596486 hasConceptScore W2950596486C41008148 @default.
- W2950596486 hasConceptScore W2950596486C78458016 @default.
- W2950596486 hasConceptScore W2950596486C86803240 @default.
- W2950596486 hasConceptScore W2950596486C97541855 @default.
- W2950596486 hasOpenAccess W2950596486 @default.
- W2950596486 hasRelatedWork W1552148478 @default.
- W2950596486 hasRelatedWork W1590178904 @default.
- W2950596486 hasRelatedWork W1964895604 @default.
- W2950596486 hasRelatedWork W2033976720 @default.
- W2950596486 hasRelatedWork W2146957157 @default.
- W2950596486 hasRelatedWork W2156578004 @default.
- W2950596486 hasRelatedWork W2289410116 @default.
- W2950596486 hasRelatedWork W2530195778 @default.
- W2950596486 hasRelatedWork W2802184653 @default.
- W2950596486 hasRelatedWork W2950471160 @default.
- W2950596486 hasRelatedWork W2962779867 @default.
- W2950596486 hasRelatedWork W2965407115 @default.
- W2950596486 hasRelatedWork W2982306485 @default.
- W2950596486 hasRelatedWork W3057037158 @default.
- W2950596486 hasRelatedWork W3090106354 @default.
- W2950596486 hasRelatedWork W3109669325 @default.
- W2950596486 hasRelatedWork W3126916000 @default.
- W2950596486 hasRelatedWork W3131386210 @default.
- W2950596486 hasRelatedWork W3170197122 @default.
- W2950596486 hasRelatedWork W3196528513 @default.
- W2950596486 isParatext "false" @default.
- W2950596486 isRetracted "false" @default.
- W2950596486 magId "2950596486" @default.
- W2950596486 workType "article" @default.