Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221153713> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4221153713 abstract "We study the problem of unsupervised skill discovery, whose goal is to learn a set of diverse and useful skills with no external reward. There have been a number of skill discovery methods based on maximizing the mutual information (MI) between skills and states. However, we point out that their MI objectives usually prefer static skills to dynamic ones, which may hinder the application for downstream tasks. To address this issue, we propose Lipschitz-constrained Skill Discovery (LSD), which encourages the agent to discover more diverse, dynamic, and far-reaching skills. Another benefit of LSD is that its learned representation function can be utilized for solving goal-following downstream tasks even in a zero-shot manner - i.e., without further training or complex planning. Through experiments on various MuJoCo robotic locomotion and manipulation environments, we demonstrate that LSD outperforms previous approaches in terms of skill diversity, state space coverage, and performance on seven downstream tasks including the challenging task of following multiple goals on Humanoid. Our code and videos are available at https://shpark.me/projects/lsd/." @default.
- W4221153713 created "2022-04-03" @default.
- W4221153713 creator A5006868457 @default.
- W4221153713 creator A5032124306 @default.
- W4221153713 creator A5043029070 @default.
- W4221153713 creator A5049929168 @default.
- W4221153713 creator A5064419280 @default.
- W4221153713 date "2022-02-02" @default.
- W4221153713 modified "2023-09-27" @default.
- W4221153713 title "Lipschitz-constrained Unsupervised Skill Discovery" @default.
- W4221153713 doi "https://doi.org/10.48550/arxiv.2202.00914" @default.
- W4221153713 hasPublicationYear "2022" @default.
- W4221153713 type Work @default.
- W4221153713 citedByCount "0" @default.
- W4221153713 crossrefType "posted-content" @default.
- W4221153713 hasAuthorship W4221153713A5006868457 @default.
- W4221153713 hasAuthorship W4221153713A5032124306 @default.
- W4221153713 hasAuthorship W4221153713A5043029070 @default.
- W4221153713 hasAuthorship W4221153713A5049929168 @default.
- W4221153713 hasAuthorship W4221153713A5064419280 @default.
- W4221153713 hasBestOaLocation W42211537131 @default.
- W4221153713 hasConcept C111919701 @default.
- W4221153713 hasConcept C119857082 @default.
- W4221153713 hasConcept C127413603 @default.
- W4221153713 hasConcept C134306372 @default.
- W4221153713 hasConcept C14036430 @default.
- W4221153713 hasConcept C154945302 @default.
- W4221153713 hasConcept C177264268 @default.
- W4221153713 hasConcept C17744445 @default.
- W4221153713 hasConcept C199360897 @default.
- W4221153713 hasConcept C199539241 @default.
- W4221153713 hasConcept C201995342 @default.
- W4221153713 hasConcept C21547014 @default.
- W4221153713 hasConcept C22324862 @default.
- W4221153713 hasConcept C2524010 @default.
- W4221153713 hasConcept C2776207758 @default.
- W4221153713 hasConcept C2776359362 @default.
- W4221153713 hasConcept C2776760102 @default.
- W4221153713 hasConcept C2778572836 @default.
- W4221153713 hasConcept C2780451532 @default.
- W4221153713 hasConcept C28719098 @default.
- W4221153713 hasConcept C33923547 @default.
- W4221153713 hasConcept C41008148 @default.
- W4221153713 hasConcept C78458016 @default.
- W4221153713 hasConcept C86803240 @default.
- W4221153713 hasConcept C94625758 @default.
- W4221153713 hasConceptScore W4221153713C111919701 @default.
- W4221153713 hasConceptScore W4221153713C119857082 @default.
- W4221153713 hasConceptScore W4221153713C127413603 @default.
- W4221153713 hasConceptScore W4221153713C134306372 @default.
- W4221153713 hasConceptScore W4221153713C14036430 @default.
- W4221153713 hasConceptScore W4221153713C154945302 @default.
- W4221153713 hasConceptScore W4221153713C177264268 @default.
- W4221153713 hasConceptScore W4221153713C17744445 @default.
- W4221153713 hasConceptScore W4221153713C199360897 @default.
- W4221153713 hasConceptScore W4221153713C199539241 @default.
- W4221153713 hasConceptScore W4221153713C201995342 @default.
- W4221153713 hasConceptScore W4221153713C21547014 @default.
- W4221153713 hasConceptScore W4221153713C22324862 @default.
- W4221153713 hasConceptScore W4221153713C2524010 @default.
- W4221153713 hasConceptScore W4221153713C2776207758 @default.
- W4221153713 hasConceptScore W4221153713C2776359362 @default.
- W4221153713 hasConceptScore W4221153713C2776760102 @default.
- W4221153713 hasConceptScore W4221153713C2778572836 @default.
- W4221153713 hasConceptScore W4221153713C2780451532 @default.
- W4221153713 hasConceptScore W4221153713C28719098 @default.
- W4221153713 hasConceptScore W4221153713C33923547 @default.
- W4221153713 hasConceptScore W4221153713C41008148 @default.
- W4221153713 hasConceptScore W4221153713C78458016 @default.
- W4221153713 hasConceptScore W4221153713C86803240 @default.
- W4221153713 hasConceptScore W4221153713C94625758 @default.
- W4221153713 hasLocation W42211537131 @default.
- W4221153713 hasOpenAccess W4221153713 @default.
- W4221153713 hasPrimaryLocation W42211537131 @default.
- W4221153713 hasRelatedWork W127839035 @default.
- W4221153713 hasRelatedWork W1563281174 @default.
- W4221153713 hasRelatedWork W2033363980 @default.
- W4221153713 hasRelatedWork W2072834482 @default.
- W4221153713 hasRelatedWork W2355707807 @default.
- W4221153713 hasRelatedWork W2412043110 @default.
- W4221153713 hasRelatedWork W3038065642 @default.
- W4221153713 hasRelatedWork W3198856780 @default.
- W4221153713 hasRelatedWork W55678778 @default.
- W4221153713 hasRelatedWork W2184706825 @default.
- W4221153713 isParatext "false" @default.
- W4221153713 isRetracted "false" @default.
- W4221153713 workType "article" @default.