Matches in SemOpenAlex for { <https://semopenalex.org/work/W2115318338> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2115318338 endingPage "297" @default.
- W2115318338 startingPage "289" @default.
- W2115318338 abstract "We consider the problem of apprenticeship learning where the examples, demonstrated by an expert, cover only a small part of a large state space. Inverse Reinforcement Learning (IRL) provides an efficient tool for generalizing the demonstration, based on the assumption that the expert is maximizing a utility function that is a linear combination of state-action features. Most IRL algorithms use a simple Monte Carlo estimation to approximate the expected feature counts under the expert's policy. In this paper, we show that the quality of the learned policies is highly sensitive to the error in estimating the feature counts. To reduce this error, we introduce a novel approach for bootstrapping the demonstration by assuming that: (i), the expert is (near-)optimal, and (ii), the dynamics of the system is known. Empirical results on gridworlds and car racing problems show that our approach is able to learn good policies from a small number of demonstrations." @default.
- W2115318338 created "2016-06-24" @default.
- W2115318338 creator A5002976111 @default.
- W2115318338 creator A5068615270 @default.
- W2115318338 date "2010-12-06" @default.
- W2115318338 modified "2023-09-24" @default.
- W2115318338 title "Bootstrapping Apprenticeship Learning" @default.
- W2115318338 cites W1591675293 @default.
- W2115318338 cites W1999874108 @default.
- W2115318338 cites W2061562262 @default.
- W2115318338 cites W2101911972 @default.
- W2115318338 cites W2102847492 @default.
- W2115318338 cites W2113023245 @default.
- W2115318338 cites W2116442740 @default.
- W2115318338 cites W2126105931 @default.
- W2115318338 cites W2169498096 @default.
- W2115318338 hasPublicationYear "2010" @default.
- W2115318338 type Work @default.
- W2115318338 sameAs 2115318338 @default.
- W2115318338 citedByCount "6" @default.
- W2115318338 countsByYear W21153183382012 @default.
- W2115318338 countsByYear W21153183382013 @default.
- W2115318338 countsByYear W21153183382020 @default.
- W2115318338 countsByYear W21153183382021 @default.
- W2115318338 crossrefType "proceedings-article" @default.
- W2115318338 hasAuthorship W2115318338A5002976111 @default.
- W2115318338 hasAuthorship W2115318338A5068615270 @default.
- W2115318338 hasConcept C105795698 @default.
- W2115318338 hasConcept C107806365 @default.
- W2115318338 hasConcept C108583219 @default.
- W2115318338 hasConcept C111472728 @default.
- W2115318338 hasConcept C119857082 @default.
- W2115318338 hasConcept C126255220 @default.
- W2115318338 hasConcept C138885662 @default.
- W2115318338 hasConcept C149782125 @default.
- W2115318338 hasConcept C154945302 @default.
- W2115318338 hasConcept C19499675 @default.
- W2115318338 hasConcept C207609745 @default.
- W2115318338 hasConcept C2776401178 @default.
- W2115318338 hasConcept C2778827112 @default.
- W2115318338 hasConcept C2779530757 @default.
- W2115318338 hasConcept C33923547 @default.
- W2115318338 hasConcept C41008148 @default.
- W2115318338 hasConcept C41895202 @default.
- W2115318338 hasConcept C72434380 @default.
- W2115318338 hasConcept C83665646 @default.
- W2115318338 hasConcept C97541855 @default.
- W2115318338 hasConceptScore W2115318338C105795698 @default.
- W2115318338 hasConceptScore W2115318338C107806365 @default.
- W2115318338 hasConceptScore W2115318338C108583219 @default.
- W2115318338 hasConceptScore W2115318338C111472728 @default.
- W2115318338 hasConceptScore W2115318338C119857082 @default.
- W2115318338 hasConceptScore W2115318338C126255220 @default.
- W2115318338 hasConceptScore W2115318338C138885662 @default.
- W2115318338 hasConceptScore W2115318338C149782125 @default.
- W2115318338 hasConceptScore W2115318338C154945302 @default.
- W2115318338 hasConceptScore W2115318338C19499675 @default.
- W2115318338 hasConceptScore W2115318338C207609745 @default.
- W2115318338 hasConceptScore W2115318338C2776401178 @default.
- W2115318338 hasConceptScore W2115318338C2778827112 @default.
- W2115318338 hasConceptScore W2115318338C2779530757 @default.
- W2115318338 hasConceptScore W2115318338C33923547 @default.
- W2115318338 hasConceptScore W2115318338C41008148 @default.
- W2115318338 hasConceptScore W2115318338C41895202 @default.
- W2115318338 hasConceptScore W2115318338C72434380 @default.
- W2115318338 hasConceptScore W2115318338C83665646 @default.
- W2115318338 hasConceptScore W2115318338C97541855 @default.
- W2115318338 hasLocation W21153183381 @default.
- W2115318338 hasOpenAccess W2115318338 @default.
- W2115318338 hasPrimaryLocation W21153183381 @default.
- W2115318338 hasRelatedWork W1591675293 @default.
- W2115318338 hasRelatedWork W184546935 @default.
- W2115318338 hasRelatedWork W1971913572 @default.
- W2115318338 hasRelatedWork W1999874108 @default.
- W2115318338 hasRelatedWork W2061562262 @default.
- W2115318338 hasRelatedWork W2074416206 @default.
- W2115318338 hasRelatedWork W2096846143 @default.
- W2115318338 hasRelatedWork W2096871511 @default.
- W2115318338 hasRelatedWork W2098774185 @default.
- W2115318338 hasRelatedWork W2102847492 @default.
- W2115318338 hasRelatedWork W2113023245 @default.
- W2115318338 hasRelatedWork W2116442740 @default.
- W2115318338 hasRelatedWork W2133068870 @default.
- W2115318338 hasRelatedWork W2134491302 @default.
- W2115318338 hasRelatedWork W2169498096 @default.
- W2115318338 hasRelatedWork W2181849516 @default.
- W2115318338 hasRelatedWork W2305870132 @default.
- W2115318338 hasRelatedWork W2950182411 @default.
- W2115318338 hasRelatedWork W2964218708 @default.
- W2115318338 hasRelatedWork W3180220823 @default.
- W2115318338 hasVolume "23" @default.
- W2115318338 isParatext "false" @default.
- W2115318338 isRetracted "false" @default.
- W2115318338 magId "2115318338" @default.
- W2115318338 workType "article" @default.