Matches in SemOpenAlex for { <https://semopenalex.org/work/W2165792602> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2165792602 endingPage "1029" @default.
- W2165792602 startingPage "1024" @default.
- W2165792602 abstract "Temporal-difference reinforcement learning (RL) has been successfully applied in several domains with large state sets. Large action sets, however, have received considerably less attention. This paper demonstrates the use of knowledge transfer between related tasks to accelerate learning with large action sets. We introduce action transfer, a technique that extracts the actions from the (near-)optimal solution to the first task and uses them in place of the full action set when learning any subsequent tasks. When optimal actions make up a small fraction of the domain's action set, action transfer can substantially reduce the number of actions and thus the complexity of the problem. However, action transfer between dissimilar tasks can be detrimental. To address this difficulty, we contribute randomized task perturbation (RTP), an enhancement to action transfer that makes it robust to unrepresentative source tasks. We motivate RTP action transfer with a detailed theoretical analysis featuring a formalism of related tasks and a bound on the suboptimality of action transfer. The empirical results in this paper show the potential of RTP action transfer to substantially expand the applicability of RL to problems with large action sets." @default.
- W2165792602 created "2016-06-24" @default.
- W2165792602 creator A5001594330 @default.
- W2165792602 creator A5079755716 @default.
- W2165792602 date "2005-07-09" @default.
- W2165792602 modified "2023-09-24" @default.
- W2165792602 title "Improving action selection in MDP's via knowledge transfer" @default.
- W2165792602 cites W1515851193 @default.
- W2165792602 cites W1631187438 @default.
- W2165792602 cites W1800916125 @default.
- W2165792602 cites W2041367235 @default.
- W2165792602 cites W2117341272 @default.
- W2165792602 cites W2121517924 @default.
- W2165792602 cites W2121863487 @default.
- W2165792602 cites W2134153324 @default.
- W2165792602 cites W2154549708 @default.
- W2165792602 cites W2155791599 @default.
- W2165792602 cites W2160279936 @default.
- W2165792602 cites W3011120880 @default.
- W2165792602 hasPublicationYear "2005" @default.
- W2165792602 type Work @default.
- W2165792602 sameAs 2165792602 @default.
- W2165792602 citedByCount "46" @default.
- W2165792602 countsByYear W21657926022012 @default.
- W2165792602 countsByYear W21657926022013 @default.
- W2165792602 countsByYear W21657926022014 @default.
- W2165792602 countsByYear W21657926022015 @default.
- W2165792602 countsByYear W21657926022016 @default.
- W2165792602 countsByYear W21657926022017 @default.
- W2165792602 countsByYear W21657926022018 @default.
- W2165792602 countsByYear W21657926022019 @default.
- W2165792602 countsByYear W21657926022020 @default.
- W2165792602 countsByYear W21657926022021 @default.
- W2165792602 crossrefType "proceedings-article" @default.
- W2165792602 hasAuthorship W2165792602A5001594330 @default.
- W2165792602 hasAuthorship W2165792602A5079755716 @default.
- W2165792602 hasConcept C119857082 @default.
- W2165792602 hasConcept C121332964 @default.
- W2165792602 hasConcept C127413603 @default.
- W2165792602 hasConcept C150899416 @default.
- W2165792602 hasConcept C154945302 @default.
- W2165792602 hasConcept C166109690 @default.
- W2165792602 hasConcept C169760540 @default.
- W2165792602 hasConcept C177264268 @default.
- W2165792602 hasConcept C199360897 @default.
- W2165792602 hasConcept C201995342 @default.
- W2165792602 hasConcept C26760741 @default.
- W2165792602 hasConcept C2780451532 @default.
- W2165792602 hasConcept C2780791683 @default.
- W2165792602 hasConcept C41008148 @default.
- W2165792602 hasConcept C62520636 @default.
- W2165792602 hasConcept C86803240 @default.
- W2165792602 hasConcept C97541855 @default.
- W2165792602 hasConceptScore W2165792602C119857082 @default.
- W2165792602 hasConceptScore W2165792602C121332964 @default.
- W2165792602 hasConceptScore W2165792602C127413603 @default.
- W2165792602 hasConceptScore W2165792602C150899416 @default.
- W2165792602 hasConceptScore W2165792602C154945302 @default.
- W2165792602 hasConceptScore W2165792602C166109690 @default.
- W2165792602 hasConceptScore W2165792602C169760540 @default.
- W2165792602 hasConceptScore W2165792602C177264268 @default.
- W2165792602 hasConceptScore W2165792602C199360897 @default.
- W2165792602 hasConceptScore W2165792602C201995342 @default.
- W2165792602 hasConceptScore W2165792602C26760741 @default.
- W2165792602 hasConceptScore W2165792602C2780451532 @default.
- W2165792602 hasConceptScore W2165792602C2780791683 @default.
- W2165792602 hasConceptScore W2165792602C41008148 @default.
- W2165792602 hasConceptScore W2165792602C62520636 @default.
- W2165792602 hasConceptScore W2165792602C86803240 @default.
- W2165792602 hasConceptScore W2165792602C97541855 @default.
- W2165792602 hasLocation W21657926021 @default.
- W2165792602 hasOpenAccess W2165792602 @default.
- W2165792602 hasPrimaryLocation W21657926021 @default.
- W2165792602 hasRelatedWork W1492014007 @default.
- W2165792602 hasRelatedWork W1515851193 @default.
- W2165792602 hasRelatedWork W158722652 @default.
- W2165792602 hasRelatedWork W1598052524 @default.
- W2165792602 hasRelatedWork W1607318605 @default.
- W2165792602 hasRelatedWork W2004030284 @default.
- W2165792602 hasRelatedWork W2097381042 @default.
- W2165792602 hasRelatedWork W2109910161 @default.
- W2165792602 hasRelatedWork W2110292307 @default.
- W2165792602 hasRelatedWork W2121863487 @default.
- W2165792602 hasRelatedWork W2126565096 @default.
- W2165792602 hasRelatedWork W2128905965 @default.
- W2165792602 hasRelatedWork W2143435603 @default.
- W2165792602 hasRelatedWork W2154328025 @default.
- W2165792602 hasRelatedWork W2158150115 @default.
- W2165792602 hasRelatedWork W2161795906 @default.
- W2165792602 hasRelatedWork W2164114810 @default.
- W2165792602 hasRelatedWork W2165698076 @default.
- W2165792602 hasRelatedWork W2169743339 @default.
- W2165792602 hasRelatedWork W3103256699 @default.
- W2165792602 isParatext "false" @default.
- W2165792602 isRetracted "false" @default.
- W2165792602 magId "2165792602" @default.
- W2165792602 workType "article" @default.