Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208793005> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3208793005 abstract "The recent history of machine learning research has taught us that machine learning methods can be most effective when they are provided with very large, high-capacity models, and trained on very large and diverse datasets. This has spurred the community to search for ways to remove any bottlenecks to scale. Often the foremost among such bottlenecks is the need for human effort, including the effort of curating and labeling datasets. As a result, considerable attention in recent years has been devoted to utilizing unlabeled data, which can be collected in vast quantities. However, some of the most widely used methods for training on such unlabeled data themselves require human-designed objective functions that must correlate in some meaningful way to downstream tasks. I will argue that a general, principled, and powerful framework for utilizing unlabeled data can be derived from reinforcement learning, using general purpose unsupervised or self-supervised reinforcement learning objectives in concert with offline reinforcement learning methods that can leverage large datasets. I will discuss how such a procedure is more closely aligned with potential downstream tasks, and how it could build on existing techniques that have been developed in recent years." @default.
- W3208793005 created "2021-11-08" @default.
- W3208793005 creator A5026322200 @default.
- W3208793005 date "2021-10-24" @default.
- W3208793005 modified "2023-09-27" @default.
- W3208793005 title "Understanding the World Through Action." @default.
- W3208793005 cites W1527213311 @default.
- W3208793005 cites W1594201624 @default.
- W3208793005 cites W1786044565 @default.
- W3208793005 cites W2056354534 @default.
- W3208793005 cites W2151083897 @default.
- W3208793005 cites W2160815625 @default.
- W3208793005 cites W2556477470 @default.
- W3208793005 cites W2787560479 @default.
- W3208793005 cites W2787757704 @default.
- W3208793005 cites W2810785043 @default.
- W3208793005 cites W2922007426 @default.
- W3208793005 cites W2947150733 @default.
- W3208793005 cites W2949888546 @default.
- W3208793005 cites W2951557330 @default.
- W3208793005 cites W2954142106 @default.
- W3208793005 cites W2963276097 @default.
- W3208793005 cites W2963305465 @default.
- W3208793005 cites W2963341956 @default.
- W3208793005 cites W2963438456 @default.
- W3208793005 cites W2971262355 @default.
- W3208793005 cites W3005680577 @default.
- W3208793005 cites W3022566517 @default.
- W3208793005 cites W3033324992 @default.
- W3208793005 cites W3034786558 @default.
- W3208793005 cites W3095178267 @default.
- W3208793005 cites W3115080916 @default.
- W3208793005 cites W3127247709 @default.
- W3208793005 cites W3132577852 @default.
- W3208793005 cites W3152568156 @default.
- W3208793005 cites W3156232699 @default.
- W3208793005 cites W3156705940 @default.
- W3208793005 hasPublicationYear "2021" @default.
- W3208793005 type Work @default.
- W3208793005 sameAs 3208793005 @default.
- W3208793005 citedByCount "0" @default.
- W3208793005 crossrefType "posted-content" @default.
- W3208793005 hasAuthorship W3208793005A5026322200 @default.
- W3208793005 hasConcept C119857082 @default.
- W3208793005 hasConcept C121332964 @default.
- W3208793005 hasConcept C153083717 @default.
- W3208793005 hasConcept C154945302 @default.
- W3208793005 hasConcept C2522767166 @default.
- W3208793005 hasConcept C2776145971 @default.
- W3208793005 hasConcept C2780791683 @default.
- W3208793005 hasConcept C41008148 @default.
- W3208793005 hasConcept C62520636 @default.
- W3208793005 hasConcept C97541855 @default.
- W3208793005 hasConceptScore W3208793005C119857082 @default.
- W3208793005 hasConceptScore W3208793005C121332964 @default.
- W3208793005 hasConceptScore W3208793005C153083717 @default.
- W3208793005 hasConceptScore W3208793005C154945302 @default.
- W3208793005 hasConceptScore W3208793005C2522767166 @default.
- W3208793005 hasConceptScore W3208793005C2776145971 @default.
- W3208793005 hasConceptScore W3208793005C2780791683 @default.
- W3208793005 hasConceptScore W3208793005C41008148 @default.
- W3208793005 hasConceptScore W3208793005C62520636 @default.
- W3208793005 hasConceptScore W3208793005C97541855 @default.
- W3208793005 hasLocation W32087930051 @default.
- W3208793005 hasOpenAccess W3208793005 @default.
- W3208793005 hasPrimaryLocation W32087930051 @default.
- W3208793005 hasRelatedWork W133394268 @default.
- W3208793005 hasRelatedWork W2143337117 @default.
- W3208793005 hasRelatedWork W2266167825 @default.
- W3208793005 hasRelatedWork W2543818344 @default.
- W3208793005 hasRelatedWork W2736818646 @default.
- W3208793005 hasRelatedWork W2758343255 @default.
- W3208793005 hasRelatedWork W2810410758 @default.
- W3208793005 hasRelatedWork W2899991543 @default.
- W3208793005 hasRelatedWork W2966318169 @default.
- W3208793005 hasRelatedWork W2969000136 @default.
- W3208793005 hasRelatedWork W2988627372 @default.
- W3208793005 hasRelatedWork W3008176773 @default.
- W3208793005 hasRelatedWork W3013377162 @default.
- W3208793005 hasRelatedWork W3021676282 @default.
- W3208793005 hasRelatedWork W3113366607 @default.
- W3208793005 hasRelatedWork W3123279568 @default.
- W3208793005 hasRelatedWork W3126613720 @default.
- W3208793005 hasRelatedWork W3131671190 @default.
- W3208793005 hasRelatedWork W3175413749 @default.
- W3208793005 hasRelatedWork W629538245 @default.
- W3208793005 isParatext "false" @default.
- W3208793005 isRetracted "false" @default.
- W3208793005 magId "3208793005" @default.
- W3208793005 workType "article" @default.