Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962808049> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2962808049 endingPage "997" @default.
- W2962808049 startingPage "989" @default.
- W2962808049 abstract "Transfer learning can greatly speed up reinforcement learning for a new task by leveraging policies of relevant tasks. Existing works of policy reuse either focus on selecting a single best source policy for reuse without considering contexts, or fail to guarantee learning an optimal policy for a target task. To improve transfer efficiency and guarantee optimality, we develop a novel policy reuse method, called Context-Aware Policy reuSe (CAPS), that enables multi-policy reuse. Our method learns when and which source policy is best for reuse, as well as when to terminate its reuse. CAPS provides theoretical guarantees in convergence and optimality for both source policy selection and target task learning. Empirical results on a grid-based navigation domain and the Pygame Learning Environment demonstrate that CAPS significantly outperforms other state-of-the-art policy reuse methods." @default.
- W2962808049 created "2019-07-30" @default.
- W2962808049 creator A5010176958 @default.
- W2962808049 creator A5055640195 @default.
- W2962808049 creator A5058967117 @default.
- W2962808049 creator A5087540449 @default.
- W2962808049 date "2019-05-08" @default.
- W2962808049 modified "2023-09-27" @default.
- W2962808049 title "Context-Aware Policy Reuse" @default.
- W2962808049 hasPublicationYear "2019" @default.
- W2962808049 type Work @default.
- W2962808049 sameAs 2962808049 @default.
- W2962808049 citedByCount "6" @default.
- W2962808049 countsByYear W29628080492020 @default.
- W2962808049 countsByYear W29628080492021 @default.
- W2962808049 countsByYear W29628080492022 @default.
- W2962808049 crossrefType "proceedings-article" @default.
- W2962808049 hasAuthorship W2962808049A5010176958 @default.
- W2962808049 hasAuthorship W2962808049A5055640195 @default.
- W2962808049 hasAuthorship W2962808049A5058967117 @default.
- W2962808049 hasAuthorship W2962808049A5087540449 @default.
- W2962808049 hasConcept C107457646 @default.
- W2962808049 hasConcept C119857082 @default.
- W2962808049 hasConcept C127413603 @default.
- W2962808049 hasConcept C134306372 @default.
- W2962808049 hasConcept C150899416 @default.
- W2962808049 hasConcept C151730666 @default.
- W2962808049 hasConcept C154945302 @default.
- W2962808049 hasConcept C201995342 @default.
- W2962808049 hasConcept C206588197 @default.
- W2962808049 hasConcept C2779343474 @default.
- W2962808049 hasConcept C2780451532 @default.
- W2962808049 hasConcept C33923547 @default.
- W2962808049 hasConcept C36503486 @default.
- W2962808049 hasConcept C41008148 @default.
- W2962808049 hasConcept C548081761 @default.
- W2962808049 hasConcept C86803240 @default.
- W2962808049 hasConcept C97541855 @default.
- W2962808049 hasConceptScore W2962808049C107457646 @default.
- W2962808049 hasConceptScore W2962808049C119857082 @default.
- W2962808049 hasConceptScore W2962808049C127413603 @default.
- W2962808049 hasConceptScore W2962808049C134306372 @default.
- W2962808049 hasConceptScore W2962808049C150899416 @default.
- W2962808049 hasConceptScore W2962808049C151730666 @default.
- W2962808049 hasConceptScore W2962808049C154945302 @default.
- W2962808049 hasConceptScore W2962808049C201995342 @default.
- W2962808049 hasConceptScore W2962808049C206588197 @default.
- W2962808049 hasConceptScore W2962808049C2779343474 @default.
- W2962808049 hasConceptScore W2962808049C2780451532 @default.
- W2962808049 hasConceptScore W2962808049C33923547 @default.
- W2962808049 hasConceptScore W2962808049C36503486 @default.
- W2962808049 hasConceptScore W2962808049C41008148 @default.
- W2962808049 hasConceptScore W2962808049C548081761 @default.
- W2962808049 hasConceptScore W2962808049C86803240 @default.
- W2962808049 hasConceptScore W2962808049C97541855 @default.
- W2962808049 hasLocation W29628080491 @default.
- W2962808049 hasOpenAccess W2962808049 @default.
- W2962808049 hasPrimaryLocation W29628080491 @default.
- W2962808049 hasRelatedWork W1965993844 @default.
- W2962808049 hasRelatedWork W1992925627 @default.
- W2962808049 hasRelatedWork W2031727428 @default.
- W2962808049 hasRelatedWork W2097381042 @default.
- W2962808049 hasRelatedWork W2115714256 @default.
- W2962808049 hasRelatedWork W2569013745 @default.
- W2962808049 hasRelatedWork W2775322888 @default.
- W2962808049 hasRelatedWork W2778197332 @default.
- W2962808049 hasRelatedWork W2797234205 @default.
- W2962808049 hasRelatedWork W2897086622 @default.
- W2962808049 hasRelatedWork W2941439950 @default.
- W2962808049 hasRelatedWork W2963065769 @default.
- W2962808049 hasRelatedWork W2963170138 @default.
- W2962808049 hasRelatedWork W2965244411 @default.
- W2962808049 hasRelatedWork W2985909959 @default.
- W2962808049 hasRelatedWork W2995874959 @default.
- W2962808049 hasRelatedWork W3002908178 @default.
- W2962808049 hasRelatedWork W3021496363 @default.
- W2962808049 hasRelatedWork W3037540495 @default.
- W2962808049 hasRelatedWork W3153918841 @default.
- W2962808049 isParatext "false" @default.
- W2962808049 isRetracted "false" @default.
- W2962808049 magId "2962808049" @default.
- W2962808049 workType "article" @default.