Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213154883> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3213154883 abstract "In reinforcement learning, pre-trained low-level skills have the potential to greatly facilitate exploration. However, prior knowledge of the downstream task is required to strike the right balance between generality (fine-grained control) and specificity (faster learning) in skill design. In previous work on continuous control, the sensitivity of methods to this trade-off has not been addressed explicitly, as locomotion provides a suitable prior for navigation tasks, which have been of foremost interest. In this work, we analyze this trade-off for low-level policy pre-training with a new benchmark suite of diverse, sparse-reward tasks for bipedal robots. We alleviate the need for prior knowledge by proposing a hierarchical skill learning framework that acquires skills of varying complexity in an unsupervised manner. For utilization on downstream tasks, we present a three-layered hierarchical learning algorithm to automatically trade off between general and specific skills as required by the respective task. In our experiments, we show that our approach performs this trade-off effectively and achieves better results than current state-of-the-art methods for end-to-end hierarchical reinforcement learning and unsupervised skill discovery." @default.
- W3213154883 created "2021-11-22" @default.
- W3213154883 creator A5003040843 @default.
- W3213154883 creator A5041907084 @default.
- W3213154883 creator A5069183549 @default.
- W3213154883 creator A5084360449 @default.
- W3213154883 date "2021-12-06" @default.
- W3213154883 modified "2023-09-29" @default.
- W3213154883 title "Hierarchical Skills for Efficient Exploration" @default.
- W3213154883 hasPublicationYear "2021" @default.
- W3213154883 type Work @default.
- W3213154883 sameAs 3213154883 @default.
- W3213154883 citedByCount "0" @default.
- W3213154883 crossrefType "proceedings-article" @default.
- W3213154883 hasAuthorship W3213154883A5003040843 @default.
- W3213154883 hasAuthorship W3213154883A5041907084 @default.
- W3213154883 hasAuthorship W3213154883A5069183549 @default.
- W3213154883 hasAuthorship W3213154883A5084360449 @default.
- W3213154883 hasConcept C119857082 @default.
- W3213154883 hasConcept C127413603 @default.
- W3213154883 hasConcept C13280743 @default.
- W3213154883 hasConcept C154945302 @default.
- W3213154883 hasConcept C15744967 @default.
- W3213154883 hasConcept C166957645 @default.
- W3213154883 hasConcept C175154964 @default.
- W3213154883 hasConcept C185798385 @default.
- W3213154883 hasConcept C201995342 @default.
- W3213154883 hasConcept C205649164 @default.
- W3213154883 hasConcept C2775924081 @default.
- W3213154883 hasConcept C2780451532 @default.
- W3213154883 hasConcept C2780767217 @default.
- W3213154883 hasConcept C41008148 @default.
- W3213154883 hasConcept C542102704 @default.
- W3213154883 hasConcept C79581498 @default.
- W3213154883 hasConcept C8038995 @default.
- W3213154883 hasConcept C95457728 @default.
- W3213154883 hasConcept C97541855 @default.
- W3213154883 hasConceptScore W3213154883C119857082 @default.
- W3213154883 hasConceptScore W3213154883C127413603 @default.
- W3213154883 hasConceptScore W3213154883C13280743 @default.
- W3213154883 hasConceptScore W3213154883C154945302 @default.
- W3213154883 hasConceptScore W3213154883C15744967 @default.
- W3213154883 hasConceptScore W3213154883C166957645 @default.
- W3213154883 hasConceptScore W3213154883C175154964 @default.
- W3213154883 hasConceptScore W3213154883C185798385 @default.
- W3213154883 hasConceptScore W3213154883C201995342 @default.
- W3213154883 hasConceptScore W3213154883C205649164 @default.
- W3213154883 hasConceptScore W3213154883C2775924081 @default.
- W3213154883 hasConceptScore W3213154883C2780451532 @default.
- W3213154883 hasConceptScore W3213154883C2780767217 @default.
- W3213154883 hasConceptScore W3213154883C41008148 @default.
- W3213154883 hasConceptScore W3213154883C542102704 @default.
- W3213154883 hasConceptScore W3213154883C79581498 @default.
- W3213154883 hasConceptScore W3213154883C8038995 @default.
- W3213154883 hasConceptScore W3213154883C95457728 @default.
- W3213154883 hasConceptScore W3213154883C97541855 @default.
- W3213154883 hasLocation W32131548831 @default.
- W3213154883 hasOpenAccess W3213154883 @default.
- W3213154883 hasPrimaryLocation W32131548831 @default.
- W3213154883 hasRelatedWork W2950197980 @default.
- W3213154883 hasRelatedWork W2951032747 @default.
- W3213154883 hasRelatedWork W2952897246 @default.
- W3213154883 hasRelatedWork W2954970763 @default.
- W3213154883 hasRelatedWork W2963120632 @default.
- W3213154883 hasRelatedWork W2963286043 @default.
- W3213154883 hasRelatedWork W2968058821 @default.
- W3213154883 hasRelatedWork W3003653070 @default.
- W3213154883 hasRelatedWork W3021105371 @default.
- W3213154883 hasRelatedWork W3084024636 @default.
- W3213154883 hasRelatedWork W3093201525 @default.
- W3213154883 hasRelatedWork W3103763075 @default.
- W3213154883 hasRelatedWork W3124128931 @default.
- W3213154883 hasRelatedWork W3130027291 @default.
- W3213154883 hasRelatedWork W3170838936 @default.
- W3213154883 hasRelatedWork W3184369601 @default.
- W3213154883 hasRelatedWork W3199013988 @default.
- W3213154883 hasRelatedWork W3203056473 @default.
- W3213154883 hasRelatedWork W3207823504 @default.
- W3213154883 hasRelatedWork W2912290695 @default.
- W3213154883 hasVolume "34" @default.
- W3213154883 isParatext "false" @default.
- W3213154883 isRetracted "false" @default.
- W3213154883 magId "3213154883" @default.
- W3213154883 workType "article" @default.