Matches in SemOpenAlex for { <https://semopenalex.org/work/W2993335794> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2993335794 abstract "One of the key approaches to save samples when learning a policy for a reinforcement learning problem is to use knowledge from an approximate model such as its simulator. However, does knowledge transfer from approximate models always help to learn a better policy? Despite numerous empirical studies of transfer reinforcement learning, an answer to this question is still elusive. In this paper, we provide a strong negative result, showing that even the full knowledge of an approximate model may not help reduce the number of samples for learning an accurate policy of the true model. We construct an example of reinforcement learning models and show that the complexity with or without knowledge transfer has the same order. On the bright side, effective knowledge transferring is still possible under additional assumptions. In particular, we demonstrate that knowing the (linear) bases of the true model significantly reduces the number of samples for learning an accurate policy." @default.
- W2993335794 created "2019-12-13" @default.
- W2993335794 creator A5013302721 @default.
- W2993335794 creator A5072096775 @default.
- W2993335794 creator A5085908411 @default.
- W2993335794 date "2019-12-06" @default.
- W2993335794 modified "2023-09-27" @default.
- W2993335794 title "Does Knowledge Transfer Always Help to Learn a Better Policy" @default.
- W2993335794 cites W2762872434 @default.
- W2993335794 cites W2805861379 @default.
- W2993335794 hasPublicationYear "2019" @default.
- W2993335794 type Work @default.
- W2993335794 sameAs 2993335794 @default.
- W2993335794 citedByCount "3" @default.
- W2993335794 countsByYear W29933357942020 @default.
- W2993335794 countsByYear W29933357942021 @default.
- W2993335794 crossrefType "posted-content" @default.
- W2993335794 hasAuthorship W2993335794A5013302721 @default.
- W2993335794 hasAuthorship W2993335794A5072096775 @default.
- W2993335794 hasAuthorship W2993335794A5085908411 @default.
- W2993335794 hasConcept C10138342 @default.
- W2993335794 hasConcept C111472728 @default.
- W2993335794 hasConcept C119857082 @default.
- W2993335794 hasConcept C138885662 @default.
- W2993335794 hasConcept C150899416 @default.
- W2993335794 hasConcept C154945302 @default.
- W2993335794 hasConcept C162324750 @default.
- W2993335794 hasConcept C166052673 @default.
- W2993335794 hasConcept C182306322 @default.
- W2993335794 hasConcept C199360897 @default.
- W2993335794 hasConcept C26517878 @default.
- W2993335794 hasConcept C2776960227 @default.
- W2993335794 hasConcept C2779436431 @default.
- W2993335794 hasConcept C2780801425 @default.
- W2993335794 hasConcept C38652104 @default.
- W2993335794 hasConcept C41008148 @default.
- W2993335794 hasConcept C56739046 @default.
- W2993335794 hasConcept C97541855 @default.
- W2993335794 hasConceptScore W2993335794C10138342 @default.
- W2993335794 hasConceptScore W2993335794C111472728 @default.
- W2993335794 hasConceptScore W2993335794C119857082 @default.
- W2993335794 hasConceptScore W2993335794C138885662 @default.
- W2993335794 hasConceptScore W2993335794C150899416 @default.
- W2993335794 hasConceptScore W2993335794C154945302 @default.
- W2993335794 hasConceptScore W2993335794C162324750 @default.
- W2993335794 hasConceptScore W2993335794C166052673 @default.
- W2993335794 hasConceptScore W2993335794C182306322 @default.
- W2993335794 hasConceptScore W2993335794C199360897 @default.
- W2993335794 hasConceptScore W2993335794C26517878 @default.
- W2993335794 hasConceptScore W2993335794C2776960227 @default.
- W2993335794 hasConceptScore W2993335794C2779436431 @default.
- W2993335794 hasConceptScore W2993335794C2780801425 @default.
- W2993335794 hasConceptScore W2993335794C38652104 @default.
- W2993335794 hasConceptScore W2993335794C41008148 @default.
- W2993335794 hasConceptScore W2993335794C56739046 @default.
- W2993335794 hasConceptScore W2993335794C97541855 @default.
- W2993335794 hasLocation W29933357941 @default.
- W2993335794 hasOpenAccess W2993335794 @default.
- W2993335794 hasPrimaryLocation W29933357941 @default.
- W2993335794 hasRelatedWork W1484701502 @default.
- W2993335794 hasRelatedWork W1949834515 @default.
- W2993335794 hasRelatedWork W1968197408 @default.
- W2993335794 hasRelatedWork W2103235543 @default.
- W2993335794 hasRelatedWork W2126583476 @default.
- W2993335794 hasRelatedWork W2289079211 @default.
- W2993335794 hasRelatedWork W2289360150 @default.
- W2993335794 hasRelatedWork W2403755232 @default.
- W2993335794 hasRelatedWork W2770024286 @default.
- W2993335794 hasRelatedWork W2895118614 @default.
- W2993335794 hasRelatedWork W2917204536 @default.
- W2993335794 hasRelatedWork W2934523877 @default.
- W2993335794 hasRelatedWork W2945663551 @default.
- W2993335794 hasRelatedWork W2963799536 @default.
- W2993335794 hasRelatedWork W2965046886 @default.
- W2993335794 hasRelatedWork W2970384066 @default.
- W2993335794 hasRelatedWork W3022259484 @default.
- W2993335794 hasRelatedWork W3122300135 @default.
- W2993335794 hasRelatedWork W3189037857 @default.
- W2993335794 hasRelatedWork W3208182685 @default.
- W2993335794 isParatext "false" @default.
- W2993335794 isRetracted "false" @default.
- W2993335794 magId "2993335794" @default.
- W2993335794 workType "article" @default.