Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387076474> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4387076474 abstract "Long-horizon manipulation tasks such as stacking represent a longstanding challenge in the field of robotic manipulation, particularly when using reinforcement learning (RL) methods which often struggle to learn the correct sequence of actions for achieving these complex goals. To learn this sequence, symbolic planning methods offer a good solution based on high-level reasoning, however, planners often fall short in addressing the low-level control specificity needed for precise execution. This paper introduces a novel framework that integrates symbolic planning with hierarchical RL through the cooperation of high-level operators and low-level policies. Our contribution integrates planning operators (e.g. preconditions and effects) as part of the hierarchical RL algorithm based on the Scheduled Auxiliary Control (SAC-X) method. We developed a dual-purpose high-level operator, which can be used both in holistic planning and as independent, reusable policies. Our approach offers a flexible solution for long-horizon tasks, e.g., stacking a cube. The experimental results show that our proposed method obtained an average of 97.2% success rate for learning and executing the whole stack sequence, and the success rate for learning independent policies, e.g. reach (98.9%), lift (99.7%), stack (85%), etc. The training time is also reduced by 68% when using our proposed approach." @default.
- W4387076474 created "2023-09-27" @default.
- W4387076474 creator A5001769286 @default.
- W4387076474 creator A5021390512 @default.
- W4387076474 date "2023-09-25" @default.
- W4387076474 modified "2023-09-28" @default.
- W4387076474 title "Hierarchical Reinforcement Learning based on Planning Operators" @default.
- W4387076474 doi "https://doi.org/10.48550/arxiv.2309.14237" @default.
- W4387076474 hasPublicationYear "2023" @default.
- W4387076474 type Work @default.
- W4387076474 citedByCount "0" @default.
- W4387076474 crossrefType "posted-content" @default.
- W4387076474 hasAuthorship W4387076474A5001769286 @default.
- W4387076474 hasAuthorship W4387076474A5021390512 @default.
- W4387076474 hasBestOaLocation W43870764741 @default.
- W4387076474 hasConcept C104317684 @default.
- W4387076474 hasConcept C119857082 @default.
- W4387076474 hasConcept C126255220 @default.
- W4387076474 hasConcept C139002025 @default.
- W4387076474 hasConcept C154945302 @default.
- W4387076474 hasConcept C158448853 @default.
- W4387076474 hasConcept C17020691 @default.
- W4387076474 hasConcept C185592680 @default.
- W4387076474 hasConcept C199360897 @default.
- W4387076474 hasConcept C202444582 @default.
- W4387076474 hasConcept C2775924081 @default.
- W4387076474 hasConcept C2778112365 @default.
- W4387076474 hasConcept C28761237 @default.
- W4387076474 hasConcept C33923547 @default.
- W4387076474 hasConcept C41008148 @default.
- W4387076474 hasConcept C54355233 @default.
- W4387076474 hasConcept C55493867 @default.
- W4387076474 hasConcept C86339819 @default.
- W4387076474 hasConcept C86803240 @default.
- W4387076474 hasConcept C9395851 @default.
- W4387076474 hasConcept C9652623 @default.
- W4387076474 hasConcept C97541855 @default.
- W4387076474 hasConceptScore W4387076474C104317684 @default.
- W4387076474 hasConceptScore W4387076474C119857082 @default.
- W4387076474 hasConceptScore W4387076474C126255220 @default.
- W4387076474 hasConceptScore W4387076474C139002025 @default.
- W4387076474 hasConceptScore W4387076474C154945302 @default.
- W4387076474 hasConceptScore W4387076474C158448853 @default.
- W4387076474 hasConceptScore W4387076474C17020691 @default.
- W4387076474 hasConceptScore W4387076474C185592680 @default.
- W4387076474 hasConceptScore W4387076474C199360897 @default.
- W4387076474 hasConceptScore W4387076474C202444582 @default.
- W4387076474 hasConceptScore W4387076474C2775924081 @default.
- W4387076474 hasConceptScore W4387076474C2778112365 @default.
- W4387076474 hasConceptScore W4387076474C28761237 @default.
- W4387076474 hasConceptScore W4387076474C33923547 @default.
- W4387076474 hasConceptScore W4387076474C41008148 @default.
- W4387076474 hasConceptScore W4387076474C54355233 @default.
- W4387076474 hasConceptScore W4387076474C55493867 @default.
- W4387076474 hasConceptScore W4387076474C86339819 @default.
- W4387076474 hasConceptScore W4387076474C86803240 @default.
- W4387076474 hasConceptScore W4387076474C9395851 @default.
- W4387076474 hasConceptScore W4387076474C9652623 @default.
- W4387076474 hasConceptScore W4387076474C97541855 @default.
- W4387076474 hasLocation W43870764741 @default.
- W4387076474 hasOpenAccess W4387076474 @default.
- W4387076474 hasPrimaryLocation W43870764741 @default.
- W4387076474 hasRelatedWork W2348126836 @default.
- W4387076474 hasRelatedWork W260766989 @default.
- W4387076474 hasRelatedWork W2959276766 @default.
- W4387076474 hasRelatedWork W2961085424 @default.
- W4387076474 hasRelatedWork W3074294383 @default.
- W4387076474 hasRelatedWork W3139193008 @default.
- W4387076474 hasRelatedWork W4206669594 @default.
- W4387076474 hasRelatedWork W4295941380 @default.
- W4387076474 hasRelatedWork W4306674287 @default.
- W4387076474 hasRelatedWork W4319083788 @default.
- W4387076474 isParatext "false" @default.
- W4387076474 isRetracted "false" @default.
- W4387076474 workType "article" @default.