FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2899658755> ?p ?o ?g. }

• W2899658755 abstract "Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objectives. Generally, in such formulations, there is no single optimal policy which optimizes all the objectives simultaneously, and instead, a number of policies has to be found each optimizing a preference of the objectives. In other words, the MORL is framed as a meta-learning problem, with the task distribution given by a distribution over the preferences. We demonstrate that such a formulation results in a better approximation of the Pareto optimal solutions in terms of both the optimality and the computational efficiency. We evaluated our method on obtaining Pareto optimal policies using a number of continuous control problems with high degrees of freedom." @default.
• W2899658755 created "2018-11-16" @default.
• W2899658755 creator A5008171524 @default.
• W2899658755 creator A5028082686 @default.
• W2899658755 creator A5038342432 @default.
• W2899658755 creator A5082269387 @default.
• W2899658755 date "2018-11-08" @default.
• W2899658755 modified "2023-10-08" @default.
• W2899658755 title "Meta-Learning for Multi-objective Reinforcement Learning" @default.
• W2899658755 cites W1553373771 @default.
• W2899658755 cites W1585939719 @default.
• W2899658755 cites W1603565681 @default.
• W2899658755 cites W1771410628 @default.
• W2899658755 cites W1968535060 @default.
• W2899658755 cites W1987725948 @default.
• W2899658755 cites W1988210060 @default.
• W2899658755 cites W1998649829 @default.
• W2899658755 cites W2012612381 @default.
• W2899658755 cites W2044986207 @default.
• W2899658755 cites W2058192020 @default.
• W2899658755 cites W2060846151 @default.
• W2899658755 cites W2090218528 @default.
• W2899658755 cites W2126105956 @default.
• W2899658755 cites W2147995533 @default.
• W2899658755 cites W2186820913 @default.
• W2899658755 cites W2278712528 @default.
• W2899658755 cites W2592538810 @default.
• W2899658755 cites W2604763608 @default.
• W2899658755 cites W2625286567 @default.
• W2899658755 cites W2625456521 @default.
• W2899658755 cites W2733961795 @default.
• W2899658755 cites W2736601468 @default.
• W2899658755 cites W2788781499 @default.
• W2899658755 cites W2789008106 @default.
• W2899658755 cites W288089086 @default.
• W2899658755 cites W291243768 @default.
• W2899658755 cites W2949608212 @default.
• W2899658755 cites W2963641140 @default.
• W2899658755 cites W2964001908 @default.
• W2899658755 hasPublicationYear "2018" @default.
• W2899658755 type Work @default.
• W2899658755 sameAs 2899658755 @default.
• W2899658755 citedByCount "1" @default.
• W2899658755 countsByYear W28996587552020 @default.
• W2899658755 crossrefType "posted-content" @default.
• W2899658755 hasAuthorship W2899658755A5008171524 @default.
• W2899658755 hasAuthorship W2899658755A5028082686 @default.
• W2899658755 hasAuthorship W2899658755A5038342432 @default.
• W2899658755 hasAuthorship W2899658755A5082269387 @default.
• W2899658755 hasConcept C105795698 @default.
• W2899658755 hasConcept C119857082 @default.
• W2899658755 hasConcept C121332964 @default.
• W2899658755 hasConcept C126255220 @default.
• W2899658755 hasConcept C127413603 @default.
• W2899658755 hasConcept C134306372 @default.
• W2899658755 hasConcept C137635306 @default.
• W2899658755 hasConcept C154945302 @default.
• W2899658755 hasConcept C177148314 @default.
• W2899658755 hasConcept C201995342 @default.
• W2899658755 hasConcept C208081375 @default.
• W2899658755 hasConcept C2780451532 @default.
• W2899658755 hasConcept C2781002164 @default.
• W2899658755 hasConcept C2781249084 @default.
• W2899658755 hasConcept C2986314615 @default.
• W2899658755 hasConcept C33923547 @default.
• W2899658755 hasConcept C41008148 @default.
• W2899658755 hasConcept C62520636 @default.
• W2899658755 hasConcept C66938386 @default.
• W2899658755 hasConcept C67203356 @default.
• W2899658755 hasConcept C68781425 @default.
• W2899658755 hasConcept C97541855 @default.
• W2899658755 hasConceptScore W2899658755C105795698 @default.
• W2899658755 hasConceptScore W2899658755C119857082 @default.
• W2899658755 hasConceptScore W2899658755C121332964 @default.
• W2899658755 hasConceptScore W2899658755C126255220 @default.
• W2899658755 hasConceptScore W2899658755C127413603 @default.
• W2899658755 hasConceptScore W2899658755C134306372 @default.
• W2899658755 hasConceptScore W2899658755C137635306 @default.
• W2899658755 hasConceptScore W2899658755C154945302 @default.
• W2899658755 hasConceptScore W2899658755C177148314 @default.
• W2899658755 hasConceptScore W2899658755C201995342 @default.
• W2899658755 hasConceptScore W2899658755C208081375 @default.
• W2899658755 hasConceptScore W2899658755C2780451532 @default.
• W2899658755 hasConceptScore W2899658755C2781002164 @default.
• W2899658755 hasConceptScore W2899658755C2781249084 @default.
• W2899658755 hasConceptScore W2899658755C2986314615 @default.
• W2899658755 hasConceptScore W2899658755C33923547 @default.
• W2899658755 hasConceptScore W2899658755C41008148 @default.
• W2899658755 hasConceptScore W2899658755C62520636 @default.
• W2899658755 hasConceptScore W2899658755C66938386 @default.
• W2899658755 hasConceptScore W2899658755C67203356 @default.
• W2899658755 hasConceptScore W2899658755C68781425 @default.
• W2899658755 hasConceptScore W2899658755C97541855 @default.
• W2899658755 hasLocation W28996587551 @default.
• W2899658755 hasOpenAccess W2899658755 @default.
• W2899658755 hasPrimaryLocation W28996587551 @default.
• W2899658755 hasRelatedWork W1556201700 @default.
• W2899658755 hasRelatedWork W2101307636 @default.
• W2899658755 hasRelatedWork W2146957157 @default.
• W2899658755 hasRelatedWork W2151889438 @default.

• next