Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951115021> ?p ?o ?g. }
- W2951115021 abstract "We focus on the problem of learning a single motor module that can flexibly express a range of behaviors for the control of high-dimensional physically simulated humanoids. To do this, we propose a motor architecture that has the general structure of an inverse model with a latent-variable bottleneck. We show that it is possible to train this model entirely offline to compress thousands of expert policies and learn a motor primitive embedding space. The trained neural probabilistic motor primitive system can perform one-shot imitation of whole-body humanoid behaviors, robustly mimicking unseen trajectories. Additionally, we demonstrate that it is also straightforward to train controllers to reuse the learned motor primitive space to solve tasks, and the resulting movements are relatively naturalistic. To support the training of our model, we compare two approaches for offline policy cloning, including an experience efficient method which we call linear feedback policy cloning. We encourage readers to view a supplementary video ( this https URL ) summarizing our results." @default.
- W2951115021 created "2019-06-27" @default.
- W2951115021 creator A5013028446 @default.
- W2951115021 creator A5014567358 @default.
- W2951115021 creator A5039426831 @default.
- W2951115021 creator A5047996432 @default.
- W2951115021 creator A5062951341 @default.
- W2951115021 creator A5064373793 @default.
- W2951115021 creator A5067400056 @default.
- W2951115021 creator A5080814522 @default.
- W2951115021 date "2018-11-28" @default.
- W2951115021 modified "2023-09-27" @default.
- W2951115021 title "Neural probabilistic motor primitives for humanoid control" @default.
- W2951115021 cites W1637456626 @default.
- W2951115021 cites W1771410628 @default.
- W2951115021 cites W1821462560 @default.
- W2951115021 cites W1952489873 @default.
- W2951115021 cites W1959608418 @default.
- W2951115021 cites W1964946446 @default.
- W2951115021 cites W1990932462 @default.
- W2951115021 cites W2025768430 @default.
- W2951115021 cites W2035957498 @default.
- W2951115021 cites W2087617385 @default.
- W2951115021 cites W2094697451 @default.
- W2951115021 cites W2111999018 @default.
- W2951115021 cites W2134935236 @default.
- W2951115021 cites W2137558286 @default.
- W2951115021 cites W2140801763 @default.
- W2951115021 cites W2143978329 @default.
- W2951115021 cites W2158370675 @default.
- W2951115021 cites W2158782408 @default.
- W2951115021 cites W2174786457 @default.
- W2951115021 cites W2186601217 @default.
- W2951115021 cites W2296356821 @default.
- W2951115021 cites W2577981908 @default.
- W2951115021 cites W2726187156 @default.
- W2951115021 cites W2729615412 @default.
- W2951115021 cites W2739330054 @default.
- W2951115021 cites W2774527530 @default.
- W2951115021 cites W2811441028 @default.
- W2951115021 cites W2899718839 @default.
- W2951115021 cites W2900879308 @default.
- W2951115021 cites W2962734330 @default.
- W2951115021 cites W2962779270 @default.
- W2951115021 cites W2962897886 @default.
- W2951115021 cites W2962957031 @default.
- W2951115021 cites W2963094133 @default.
- W2951115021 cites W2963199420 @default.
- W2951115021 cites W2963637944 @default.
- W2951115021 cites W2963674921 @default.
- W2951115021 cites W2963921882 @default.
- W2951115021 cites W2964006217 @default.
- W2951115021 cites W2964121744 @default.
- W2951115021 hasPublicationYear "2018" @default.
- W2951115021 type Work @default.
- W2951115021 sameAs 2951115021 @default.
- W2951115021 citedByCount "0" @default.
- W2951115021 crossrefType "posted-content" @default.
- W2951115021 hasAuthorship W2951115021A5013028446 @default.
- W2951115021 hasAuthorship W2951115021A5014567358 @default.
- W2951115021 hasAuthorship W2951115021A5039426831 @default.
- W2951115021 hasAuthorship W2951115021A5047996432 @default.
- W2951115021 hasAuthorship W2951115021A5062951341 @default.
- W2951115021 hasAuthorship W2951115021A5064373793 @default.
- W2951115021 hasAuthorship W2951115021A5067400056 @default.
- W2951115021 hasAuthorship W2951115021A5080814522 @default.
- W2951115021 hasConcept C119857082 @default.
- W2951115021 hasConcept C121050878 @default.
- W2951115021 hasConcept C126388530 @default.
- W2951115021 hasConcept C137813230 @default.
- W2951115021 hasConcept C149635348 @default.
- W2951115021 hasConcept C154945302 @default.
- W2951115021 hasConcept C15744967 @default.
- W2951115021 hasConcept C169760540 @default.
- W2951115021 hasConcept C199360897 @default.
- W2951115021 hasConcept C2780513914 @default.
- W2951115021 hasConcept C41008148 @default.
- W2951115021 hasConcept C41608201 @default.
- W2951115021 hasConcept C49937458 @default.
- W2951115021 hasConcept C60692881 @default.
- W2951115021 hasConcept C77805123 @default.
- W2951115021 hasConcept C86803240 @default.
- W2951115021 hasConcept C90509273 @default.
- W2951115021 hasConceptScore W2951115021C119857082 @default.
- W2951115021 hasConceptScore W2951115021C121050878 @default.
- W2951115021 hasConceptScore W2951115021C126388530 @default.
- W2951115021 hasConceptScore W2951115021C137813230 @default.
- W2951115021 hasConceptScore W2951115021C149635348 @default.
- W2951115021 hasConceptScore W2951115021C154945302 @default.
- W2951115021 hasConceptScore W2951115021C15744967 @default.
- W2951115021 hasConceptScore W2951115021C169760540 @default.
- W2951115021 hasConceptScore W2951115021C199360897 @default.
- W2951115021 hasConceptScore W2951115021C2780513914 @default.
- W2951115021 hasConceptScore W2951115021C41008148 @default.
- W2951115021 hasConceptScore W2951115021C41608201 @default.
- W2951115021 hasConceptScore W2951115021C49937458 @default.
- W2951115021 hasConceptScore W2951115021C60692881 @default.
- W2951115021 hasConceptScore W2951115021C77805123 @default.
- W2951115021 hasConceptScore W2951115021C86803240 @default.
- W2951115021 hasConceptScore W2951115021C90509273 @default.