Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912541403> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2912541403 abstract "Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact, efficient and relevant representation of states that speeds up policy learning, reducing the number of samples needed, and that is easier to interpret. We evaluate several state representation learning methods on goal based robotics tasks and propose a new unsupervised model that stacks representations and combines strengths of several of these approaches. This method encodes all the relevant features, performs on par or better than end-to-end learning with better sample efficiency, and is robust to hyper-parameters change." @default.
- W2912541403 created "2019-02-21" @default.
- W2912541403 creator A5006026661 @default.
- W2912541403 creator A5013236820 @default.
- W2912541403 creator A5040828370 @default.
- W2912541403 creator A5048357111 @default.
- W2912541403 creator A5058176171 @default.
- W2912541403 creator A5067072090 @default.
- W2912541403 date "2019-05-06" @default.
- W2912541403 modified "2023-09-23" @default.
- W2912541403 title "Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics" @default.
- W2912541403 cites W1164749991 @default.
- W2912541403 cites W1957496711 @default.
- W2912541403 cites W1968962398 @default.
- W2912541403 cites W199564175 @default.
- W2912541403 cites W2094024286 @default.
- W2912541403 cites W2145339207 @default.
- W2912541403 cites W2266673418 @default.
- W2912541403 cites W2563830277 @default.
- W2912541403 cites W2569188995 @default.
- W2912541403 cites W2570734388 @default.
- W2912541403 cites W2614839826 @default.
- W2912541403 cites W2619484182 @default.
- W2912541403 cites W2754517384 @default.
- W2912541403 cites W2754695199 @default.
- W2912541403 cites W2787666871 @default.
- W2912541403 cites W2885550588 @default.
- W2912541403 cites W2903420114 @default.
- W2912541403 cites W2952870401 @default.
- W2912541403 cites W2963430173 @default.
- W2912541403 cites W2964001908 @default.
- W2912541403 cites W3149501923 @default.
- W2912541403 hasPublicationYear "2019" @default.
- W2912541403 type Work @default.
- W2912541403 sameAs 2912541403 @default.
- W2912541403 citedByCount "11" @default.
- W2912541403 countsByYear W29125414032019 @default.
- W2912541403 countsByYear W29125414032020 @default.
- W2912541403 countsByYear W29125414032021 @default.
- W2912541403 crossrefType "proceedings-article" @default.
- W2912541403 hasAuthorship W2912541403A5006026661 @default.
- W2912541403 hasAuthorship W2912541403A5013236820 @default.
- W2912541403 hasAuthorship W2912541403A5040828370 @default.
- W2912541403 hasAuthorship W2912541403A5048357111 @default.
- W2912541403 hasAuthorship W2912541403A5058176171 @default.
- W2912541403 hasAuthorship W2912541403A5067072090 @default.
- W2912541403 hasBestOaLocation W29125414032 @default.
- W2912541403 hasConcept C119857082 @default.
- W2912541403 hasConcept C127413603 @default.
- W2912541403 hasConcept C133731056 @default.
- W2912541403 hasConcept C154945302 @default.
- W2912541403 hasConcept C17744445 @default.
- W2912541403 hasConcept C199539241 @default.
- W2912541403 hasConcept C205606062 @default.
- W2912541403 hasConcept C2776359362 @default.
- W2912541403 hasConcept C34413123 @default.
- W2912541403 hasConcept C41008148 @default.
- W2912541403 hasConcept C52622490 @default.
- W2912541403 hasConcept C59404180 @default.
- W2912541403 hasConcept C90509273 @default.
- W2912541403 hasConcept C94625758 @default.
- W2912541403 hasConceptScore W2912541403C119857082 @default.
- W2912541403 hasConceptScore W2912541403C127413603 @default.
- W2912541403 hasConceptScore W2912541403C133731056 @default.
- W2912541403 hasConceptScore W2912541403C154945302 @default.
- W2912541403 hasConceptScore W2912541403C17744445 @default.
- W2912541403 hasConceptScore W2912541403C199539241 @default.
- W2912541403 hasConceptScore W2912541403C205606062 @default.
- W2912541403 hasConceptScore W2912541403C2776359362 @default.
- W2912541403 hasConceptScore W2912541403C34413123 @default.
- W2912541403 hasConceptScore W2912541403C41008148 @default.
- W2912541403 hasConceptScore W2912541403C52622490 @default.
- W2912541403 hasConceptScore W2912541403C59404180 @default.
- W2912541403 hasConceptScore W2912541403C90509273 @default.
- W2912541403 hasConceptScore W2912541403C94625758 @default.
- W2912541403 hasLocation W29125414031 @default.
- W2912541403 hasLocation W29125414032 @default.
- W2912541403 hasOpenAccess W2912541403 @default.
- W2912541403 hasPrimaryLocation W29125414031 @default.
- W2912541403 hasRelatedWork W2002867377 @default.
- W2912541403 hasRelatedWork W2065963568 @default.
- W2912541403 hasRelatedWork W2089011450 @default.
- W2912541403 hasRelatedWork W2104995483 @default.
- W2912541403 hasRelatedWork W2209829030 @default.
- W2912541403 hasRelatedWork W3119366040 @default.
- W2912541403 hasRelatedWork W3123210981 @default.
- W2912541403 hasRelatedWork W4285606578 @default.
- W2912541403 hasRelatedWork W4309346246 @default.
- W2912541403 hasRelatedWork W4310447957 @default.
- W2912541403 isParatext "false" @default.
- W2912541403 isRetracted "false" @default.
- W2912541403 magId "2912541403" @default.
- W2912541403 workType "article" @default.