Matches in SemOpenAlex for { <https://semopenalex.org/work/W2202140284> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2202140284 abstract "While model-based reinforcement learning is often studied under the assumption that a fully accurate model is contained within the model class, this is rarely true in practice. When the model class may be fundamentally limited, it can be difficult to obtain theoretical guarantees. Under some conditions the DAgger algorithm promises a policy nearly as good as the plan obtained from the most accurate model in the class, but only if the planning algorithm is near-optimal, which is also rarely the case in complex problems. This paper explores the interaction between DAgger and Monte Carlo planning, specifically showing that DAgger may perform poorly when coupled with a sub-optimal planner. A novel variation of DAgger specifically for use with Monte Carlo planning is derived and is shown to behave far better in some cases where DAgger fails." @default.
- W2202140284 created "2016-06-24" @default.
- W2202140284 creator A5054829924 @default.
- W2202140284 date "2015-02-21" @default.
- W2202140284 modified "2023-09-24" @default.
- W2202140284 title "Agnostic System Identification for Monte Carlo Planning" @default.
- W2202140284 cites W1625390266 @default.
- W2202140284 cites W1758031947 @default.
- W2202140284 cites W1965324089 @default.
- W2202140284 cites W2002428251 @default.
- W2202140284 cites W2012547817 @default.
- W2202140284 cites W2077052576 @default.
- W2202140284 cites W2109330238 @default.
- W2202140284 cites W2123979492 @default.
- W2202140284 cites W2126316555 @default.
- W2202140284 cites W2135997697 @default.
- W2202140284 cites W2137509429 @default.
- W2202140284 cites W2158796564 @default.
- W2202140284 cites W2163602945 @default.
- W2202140284 cites W2404689820 @default.
- W2202140284 cites W2964349150 @default.
- W2202140284 doi "https://doi.org/10.1609/aaai.v29i1.9616" @default.
- W2202140284 hasPublicationYear "2015" @default.
- W2202140284 type Work @default.
- W2202140284 sameAs 2202140284 @default.
- W2202140284 citedByCount "10" @default.
- W2202140284 countsByYear W22021402842017 @default.
- W2202140284 countsByYear W22021402842018 @default.
- W2202140284 countsByYear W22021402842020 @default.
- W2202140284 countsByYear W22021402842023 @default.
- W2202140284 crossrefType "journal-article" @default.
- W2202140284 hasAuthorship W2202140284A5054829924 @default.
- W2202140284 hasBestOaLocation W22021402842 @default.
- W2202140284 hasConcept C105795698 @default.
- W2202140284 hasConcept C116834253 @default.
- W2202140284 hasConcept C126255220 @default.
- W2202140284 hasConcept C138885662 @default.
- W2202140284 hasConcept C154945302 @default.
- W2202140284 hasConcept C166957645 @default.
- W2202140284 hasConcept C19499675 @default.
- W2202140284 hasConcept C27206212 @default.
- W2202140284 hasConcept C2776277238 @default.
- W2202140284 hasConcept C2776505523 @default.
- W2202140284 hasConcept C2776999362 @default.
- W2202140284 hasConcept C2777212361 @default.
- W2202140284 hasConcept C33923547 @default.
- W2202140284 hasConcept C41008148 @default.
- W2202140284 hasConcept C59822182 @default.
- W2202140284 hasConcept C86803240 @default.
- W2202140284 hasConcept C95457728 @default.
- W2202140284 hasConceptScore W2202140284C105795698 @default.
- W2202140284 hasConceptScore W2202140284C116834253 @default.
- W2202140284 hasConceptScore W2202140284C126255220 @default.
- W2202140284 hasConceptScore W2202140284C138885662 @default.
- W2202140284 hasConceptScore W2202140284C154945302 @default.
- W2202140284 hasConceptScore W2202140284C166957645 @default.
- W2202140284 hasConceptScore W2202140284C19499675 @default.
- W2202140284 hasConceptScore W2202140284C27206212 @default.
- W2202140284 hasConceptScore W2202140284C2776277238 @default.
- W2202140284 hasConceptScore W2202140284C2776505523 @default.
- W2202140284 hasConceptScore W2202140284C2776999362 @default.
- W2202140284 hasConceptScore W2202140284C2777212361 @default.
- W2202140284 hasConceptScore W2202140284C33923547 @default.
- W2202140284 hasConceptScore W2202140284C41008148 @default.
- W2202140284 hasConceptScore W2202140284C59822182 @default.
- W2202140284 hasConceptScore W2202140284C86803240 @default.
- W2202140284 hasConceptScore W2202140284C95457728 @default.
- W2202140284 hasIssue "1" @default.
- W2202140284 hasLocation W22021402841 @default.
- W2202140284 hasLocation W22021402842 @default.
- W2202140284 hasOpenAccess W2202140284 @default.
- W2202140284 hasPrimaryLocation W22021402841 @default.
- W2202140284 hasRelatedWork W171126145 @default.
- W2202140284 hasRelatedWork W1880350640 @default.
- W2202140284 hasRelatedWork W2077492692 @default.
- W2202140284 hasRelatedWork W2146449547 @default.
- W2202140284 hasRelatedWork W2381278952 @default.
- W2202140284 hasRelatedWork W2610446193 @default.
- W2202140284 hasRelatedWork W2762832356 @default.
- W2202140284 hasRelatedWork W56933075 @default.
- W2202140284 hasRelatedWork W618994464 @default.
- W2202140284 hasRelatedWork W75943994 @default.
- W2202140284 hasVolume "29" @default.
- W2202140284 isParatext "false" @default.
- W2202140284 isRetracted "false" @default.
- W2202140284 magId "2202140284" @default.
- W2202140284 workType "article" @default.