Matches in SemOpenAlex for { <https://semopenalex.org/work/W3108977608> ?p ?o ?g. }
- W3108977608 abstract "Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky challenge for any autonomous agent. Previous methods have used variational autoencoders to encode a scene into a low-dimensional vector that can be used as a goal for an agent to discover new skills. Nevertheless, in compositional/multi-object environments it is difficult to disentangle all the factors of variation into such a fixed-length representation of the whole scene. We propose to use object-centric representations as a modular and structured observation space, which is learned with a compositional generative world model. We show that the structure in the representations in combination with goal-conditioned attention policies helps the autonomous agent to discover and learn useful skills. These skills can be further combined to address compositional tasks like the manipulation of several different objects." @default.
- W3108977608 created "2020-12-07" @default.
- W3108977608 creator A5001474340 @default.
- W3108977608 creator A5039512035 @default.
- W3108977608 creator A5041755332 @default.
- W3108977608 date "2020-11-29" @default.
- W3108977608 modified "2023-09-23" @default.
- W3108977608 title "Self-supervised Visual Reinforcement Learning with Object-centric Representations" @default.
- W3108977608 cites W1533861849 @default.
- W3108977608 cites W2004303440 @default.
- W3108977608 cites W2158782408 @default.
- W3108977608 cites W2739083961 @default.
- W3108977608 cites W2753738274 @default.
- W3108977608 cites W2785342287 @default.
- W3108977608 cites W2786487443 @default.
- W3108977608 cites W2789062658 @default.
- W3108977608 cites W2807242871 @default.
- W3108977608 cites W2810785043 @default.
- W3108977608 cites W2903327785 @default.
- W3108977608 cites W2903538854 @default.
- W3108977608 cites W2911448865 @default.
- W3108977608 cites W2944892105 @default.
- W3108977608 cites W2948293419 @default.
- W3108977608 cites W2962736495 @default.
- W3108977608 cites W2962902376 @default.
- W3108977608 cites W2963321092 @default.
- W3108977608 cites W2963341956 @default.
- W3108977608 cites W2963403868 @default.
- W3108977608 cites W2963464736 @default.
- W3108977608 cites W2963717490 @default.
- W3108977608 cites W2964001908 @default.
- W3108977608 cites W2964021598 @default.
- W3108977608 cites W2964121744 @default.
- W3108977608 cites W2964127395 @default.
- W3108977608 cites W2964161785 @default.
- W3108977608 cites W2964213104 @default.
- W3108977608 cites W2964342357 @default.
- W3108977608 cites W2968131493 @default.
- W3108977608 cites W2970534317 @default.
- W3108977608 cites W2979103017 @default.
- W3108977608 cites W2982246413 @default.
- W3108977608 cites W2987283559 @default.
- W3108977608 cites W2995627237 @default.
- W3108977608 cites W3005680577 @default.
- W3108977608 cites W3006036127 @default.
- W3108977608 cites W3031840745 @default.
- W3108977608 cites W3032077725 @default.
- W3108977608 cites W3035161894 @default.
- W3108977608 cites W3035717769 @default.
- W3108977608 cites W3102696055 @default.
- W3108977608 cites W2971254941 @default.
- W3108977608 hasPublicationYear "2020" @default.
- W3108977608 type Work @default.
- W3108977608 sameAs 3108977608 @default.
- W3108977608 citedByCount "3" @default.
- W3108977608 countsByYear W31089776082021 @default.
- W3108977608 crossrefType "posted-content" @default.
- W3108977608 hasAuthorship W3108977608A5001474340 @default.
- W3108977608 hasAuthorship W3108977608A5039512035 @default.
- W3108977608 hasAuthorship W3108977608A5041755332 @default.
- W3108977608 hasConcept C101468663 @default.
- W3108977608 hasConcept C104317684 @default.
- W3108977608 hasConcept C107457646 @default.
- W3108977608 hasConcept C111919701 @default.
- W3108977608 hasConcept C121332964 @default.
- W3108977608 hasConcept C154945302 @default.
- W3108977608 hasConcept C17744445 @default.
- W3108977608 hasConcept C185592680 @default.
- W3108977608 hasConcept C199360897 @default.
- W3108977608 hasConcept C199539241 @default.
- W3108977608 hasConcept C2776359362 @default.
- W3108977608 hasConcept C2778334786 @default.
- W3108977608 hasConcept C2778572836 @default.
- W3108977608 hasConcept C2781238097 @default.
- W3108977608 hasConcept C39890363 @default.
- W3108977608 hasConcept C41008148 @default.
- W3108977608 hasConcept C44870925 @default.
- W3108977608 hasConcept C55493867 @default.
- W3108977608 hasConcept C66746571 @default.
- W3108977608 hasConcept C94625758 @default.
- W3108977608 hasConcept C97541855 @default.
- W3108977608 hasConceptScore W3108977608C101468663 @default.
- W3108977608 hasConceptScore W3108977608C104317684 @default.
- W3108977608 hasConceptScore W3108977608C107457646 @default.
- W3108977608 hasConceptScore W3108977608C111919701 @default.
- W3108977608 hasConceptScore W3108977608C121332964 @default.
- W3108977608 hasConceptScore W3108977608C154945302 @default.
- W3108977608 hasConceptScore W3108977608C17744445 @default.
- W3108977608 hasConceptScore W3108977608C185592680 @default.
- W3108977608 hasConceptScore W3108977608C199360897 @default.
- W3108977608 hasConceptScore W3108977608C199539241 @default.
- W3108977608 hasConceptScore W3108977608C2776359362 @default.
- W3108977608 hasConceptScore W3108977608C2778334786 @default.
- W3108977608 hasConceptScore W3108977608C2778572836 @default.
- W3108977608 hasConceptScore W3108977608C2781238097 @default.
- W3108977608 hasConceptScore W3108977608C39890363 @default.
- W3108977608 hasConceptScore W3108977608C41008148 @default.
- W3108977608 hasConceptScore W3108977608C44870925 @default.
- W3108977608 hasConceptScore W3108977608C55493867 @default.
- W3108977608 hasConceptScore W3108977608C66746571 @default.