Matches in SemOpenAlex for { <https://semopenalex.org/work/W3043649983> ?p ?o ?g. }
- W3043649983 abstract "We present a Reverse Reinforcement Learning (Reverse RL) approach for representing retrospective knowledge. General Value Functions (GVFs) have enjoyed great success in representing predictive knowledge, i.e., answering questions about possible future outcomes such as how much fuel will be consumed in expectation if we drive from A to B?. GVFs, however, cannot answer questions like how much fuel do we expect a car to have given it is at B at time $t$?. To answer this question, we need to know when that car had a full tank and how that car came to B. Since such questions emphasize the influence of possible past events on the present, we refer to their answers as retrospective knowledge. In this paper, we show how to represent retrospective knowledge with Reverse GVFs, which are trained via Reverse RL. We demonstrate empirically the utility of Reverse GVFs in both representation learning and anomaly detection." @default.
- W3043649983 created "2020-07-23" @default.
- W3043649983 creator A5004682595 @default.
- W3043649983 creator A5033834190 @default.
- W3043649983 creator A5056879203 @default.
- W3043649983 date "2020-07-09" @default.
- W3043649983 modified "2023-10-18" @default.
- W3043649983 title "Learning Retrospective Knowledge with Reverse Reinforcement Learning" @default.
- W3043649983 cites W1522301498 @default.
- W3043649983 cites W1547925194 @default.
- W3043649983 cites W1576452626 @default.
- W3043649983 cites W1594216983 @default.
- W3043649983 cites W1600293573 @default.
- W3043649983 cites W1603765807 @default.
- W3043649983 cites W1665214252 @default.
- W3043649983 cites W1967459934 @default.
- W3043649983 cites W1994616650 @default.
- W3043649983 cites W2038819732 @default.
- W3043649983 cites W2075268401 @default.
- W3043649983 cites W2100677568 @default.
- W3043649983 cites W2119567691 @default.
- W3043649983 cites W2121863487 @default.
- W3043649983 cites W2122646361 @default.
- W3043649983 cites W2132622533 @default.
- W3043649983 cites W2145339207 @default.
- W3043649983 cites W2149418961 @default.
- W3043649983 cites W2158191646 @default.
- W3043649983 cites W2158282517 @default.
- W3043649983 cites W2165905123 @default.
- W3043649983 cites W2473364827 @default.
- W3043649983 cites W2592754049 @default.
- W3043649983 cites W2739473244 @default.
- W3043649983 cites W2765302304 @default.
- W3043649983 cites W2786036274 @default.
- W3043649983 cites W2787938642 @default.
- W3043649983 cites W2788086877 @default.
- W3043649983 cites W2796054047 @default.
- W3043649983 cites W2904789544 @default.
- W3043649983 cites W2910068345 @default.
- W3043649983 cites W2949490796 @default.
- W3043649983 cites W2950872548 @default.
- W3043649983 cites W2952295663 @default.
- W3043649983 cites W2963394426 @default.
- W3043649983 cites W2963744705 @default.
- W3043649983 cites W2964112359 @default.
- W3043649983 cites W2970202659 @default.
- W3043649983 cites W2970493012 @default.
- W3043649983 cites W2970667219 @default.
- W3043649983 cites W2970717270 @default.
- W3043649983 cites W2994798986 @default.
- W3043649983 cites W3005680577 @default.
- W3043649983 cites W3032925664 @default.
- W3043649983 cites W3033987525 @default.
- W3043649983 cites W3035361730 @default.
- W3043649983 cites W3035524453 @default.
- W3043649983 cites W3035634530 @default.
- W3043649983 cites W3037621510 @default.
- W3043649983 cites W3080734044 @default.
- W3043649983 cites W3094004497 @default.
- W3043649983 cites W3115293622 @default.
- W3043649983 cites W594357522 @default.
- W3043649983 doi "https://doi.org/10.48550/arxiv.2007.06703" @default.
- W3043649983 hasPublicationYear "2020" @default.
- W3043649983 type Work @default.
- W3043649983 sameAs 3043649983 @default.
- W3043649983 citedByCount "0" @default.
- W3043649983 crossrefType "posted-content" @default.
- W3043649983 hasAuthorship W3043649983A5004682595 @default.
- W3043649983 hasAuthorship W3043649983A5033834190 @default.
- W3043649983 hasAuthorship W3043649983A5056879203 @default.
- W3043649983 hasBestOaLocation W30436499831 @default.
- W3043649983 hasConcept C119857082 @default.
- W3043649983 hasConcept C154945302 @default.
- W3043649983 hasConcept C17744445 @default.
- W3043649983 hasConcept C199539241 @default.
- W3043649983 hasConcept C2776291640 @default.
- W3043649983 hasConcept C2776359362 @default.
- W3043649983 hasConcept C41008148 @default.
- W3043649983 hasConcept C739882 @default.
- W3043649983 hasConcept C94625758 @default.
- W3043649983 hasConcept C97541855 @default.
- W3043649983 hasConceptScore W3043649983C119857082 @default.
- W3043649983 hasConceptScore W3043649983C154945302 @default.
- W3043649983 hasConceptScore W3043649983C17744445 @default.
- W3043649983 hasConceptScore W3043649983C199539241 @default.
- W3043649983 hasConceptScore W3043649983C2776291640 @default.
- W3043649983 hasConceptScore W3043649983C2776359362 @default.
- W3043649983 hasConceptScore W3043649983C41008148 @default.
- W3043649983 hasConceptScore W3043649983C739882 @default.
- W3043649983 hasConceptScore W3043649983C94625758 @default.
- W3043649983 hasConceptScore W3043649983C97541855 @default.
- W3043649983 hasLocation W30436499831 @default.
- W3043649983 hasLocation W30436499832 @default.
- W3043649983 hasOpenAccess W3043649983 @default.
- W3043649983 hasPrimaryLocation W30436499831 @default.
- W3043649983 hasRelatedWork W2923653485 @default.
- W3043649983 hasRelatedWork W2957776456 @default.
- W3043649983 hasRelatedWork W3022038857 @default.
- W3043649983 hasRelatedWork W3044458868 @default.
- W3043649983 hasRelatedWork W3088315509 @default.