FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902334345> ?p ?o ?g. }

• W2902334345 endingPage "33" @default.
• W2902334345 startingPage "25" @default.
• W2902334345 abstract "Curriculum learning in reinforcement learning is a training methodology that seeks to speed up learning of a difficult target task, by first training on a series of simpler tasks and transferring the knowledge acquired to the target task. Automatically choosing a sequence of such tasks (i.e., a curriculum) is an open problem that has been the subject of much recent work in this area. In this paper, we build upon a recent method for curriculum design, which formulates the curriculum sequencing problem as a Markov Decision Process. We extend this model to handle multiple transfer learning algorithms, and show for the first time that a curriculum policy over this MDP can be learned from experience. We explore various representations that make this possible, and evaluate our approach by learning curriculum policies for multiple agents in two different domains. The results show that our method produces curricula that can train agents to perform on a target task as fast or faster than existing methods." @default.
• W2902334345 created "2018-12-11" @default.
• W2902334345 creator A5001594330 @default.
• W2902334345 creator A5032114961 @default.
• W2902334345 date "2019-05-08" @default.
• W2902334345 modified "2023-09-23" @default.
• W2902334345 title "Learning Curriculum Policies for Reinforcement Learning" @default.
• W2902334345 cites W1515851193 @default.
• W2902334345 cites W1546944959 @default.
• W2902334345 cites W1777239053 @default.
• W2902334345 cites W1969685488 @default.
• W2902334345 cites W2097381042 @default.
• W2902334345 cites W2106008664 @default.
• W2902334345 cites W2133040789 @default.
• W2902334345 cites W2152166054 @default.
• W2902334345 cites W2164419340 @default.
• W2902334345 cites W2169743339 @default.
• W2902334345 cites W2271262891 @default.
• W2902334345 cites W2296073425 @default.
• W2902334345 cites W2476301537 @default.
• W2902334345 cites W2578423033 @default.
• W2902334345 cites W2581240229 @default.
• W2902334345 cites W2603088459 @default.
• W2902334345 cites W2605801332 @default.
• W2902334345 cites W2731828881 @default.
• W2902334345 cites W2737215407 @default.
• W2902334345 cites W2741594138 @default.
• W2902334345 cites W2751516180 @default.
• W2902334345 cites W2762242067 @default.
• W2902334345 cites W2950229905 @default.
• W2902334345 cites W2963293881 @default.
• W2902334345 hasPublicationYear "2019" @default.
• W2902334345 type Work @default.
• W2902334345 sameAs 2902334345 @default.
• W2902334345 citedByCount "33" @default.
• W2902334345 countsByYear W29023343452019 @default.
• W2902334345 countsByYear W29023343452020 @default.
• W2902334345 countsByYear W29023343452021 @default.
• W2902334345 crossrefType "proceedings-article" @default.
• W2902334345 hasAuthorship W2902334345A5001594330 @default.
• W2902334345 hasAuthorship W2902334345A5032114961 @default.
• W2902334345 hasConcept C105795698 @default.
• W2902334345 hasConcept C106189395 @default.
• W2902334345 hasConcept C111919701 @default.
• W2902334345 hasConcept C119857082 @default.
• W2902334345 hasConcept C127413603 @default.
• W2902334345 hasConcept C154945302 @default.
• W2902334345 hasConcept C15744967 @default.
• W2902334345 hasConcept C159886148 @default.
• W2902334345 hasConcept C19417346 @default.
• W2902334345 hasConcept C201995342 @default.
• W2902334345 hasConcept C2780451532 @default.
• W2902334345 hasConcept C33923547 @default.
• W2902334345 hasConcept C41008148 @default.
• W2902334345 hasConcept C47177190 @default.
• W2902334345 hasConcept C97541855 @default.
• W2902334345 hasConcept C98045186 @default.
• W2902334345 hasConceptScore W2902334345C105795698 @default.
• W2902334345 hasConceptScore W2902334345C106189395 @default.
• W2902334345 hasConceptScore W2902334345C111919701 @default.
• W2902334345 hasConceptScore W2902334345C119857082 @default.
• W2902334345 hasConceptScore W2902334345C127413603 @default.
• W2902334345 hasConceptScore W2902334345C154945302 @default.
• W2902334345 hasConceptScore W2902334345C15744967 @default.
• W2902334345 hasConceptScore W2902334345C159886148 @default.
• W2902334345 hasConceptScore W2902334345C19417346 @default.
• W2902334345 hasConceptScore W2902334345C201995342 @default.
• W2902334345 hasConceptScore W2902334345C2780451532 @default.
• W2902334345 hasConceptScore W2902334345C33923547 @default.
• W2902334345 hasConceptScore W2902334345C41008148 @default.
• W2902334345 hasConceptScore W2902334345C47177190 @default.
• W2902334345 hasConceptScore W2902334345C97541855 @default.
• W2902334345 hasConceptScore W2902334345C98045186 @default.
• W2902334345 hasLocation W29023343451 @default.
• W2902334345 hasOpenAccess W2902334345 @default.
• W2902334345 hasPrimaryLocation W29023343451 @default.
• W2902334345 hasRelatedWork W1977655452 @default.
• W2902334345 hasRelatedWork W2097381042 @default.
• W2902334345 hasRelatedWork W2121863487 @default.
• W2902334345 hasRelatedWork W2145339207 @default.
• W2902334345 hasRelatedWork W2151834591 @default.
• W2902334345 hasRelatedWork W2158782408 @default.
• W2902334345 hasRelatedWork W2296073425 @default.
• W2902334345 hasRelatedWork W2476301537 @default.
• W2902334345 hasRelatedWork W2736601468 @default.
• W2902334345 hasRelatedWork W2737215407 @default.
• W2902334345 hasRelatedWork W2741594138 @default.
• W2902334345 hasRelatedWork W2952485586 @default.
• W2902334345 hasRelatedWork W2963293881 @default.
• W2902334345 hasRelatedWork W2964001908 @default.
• W2902334345 hasRelatedWork W2964118020 @default.
• W2902334345 hasRelatedWork W2964161785 @default.
• W2902334345 hasRelatedWork W2964327384 @default.
• W2902334345 hasRelatedWork W2972758308 @default.
• W2902334345 hasRelatedWork W2978129546 @default.
• W2902334345 hasRelatedWork W567721252 @default.
• W2902334345 isParatext "false" @default.
• W2902334345 isRetracted "false" @default.

• next