Matches in SemOpenAlex for { <https://semopenalex.org/work/W2766702649> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2766702649 abstract "In reinforcement learning (RL), the guided policy search (GPS), a variant of policy search method, can encode the policy directly as well as search for optimal solutions in the policy space. Even though this algorithm is provided with asymptotic local convergence guarantees, it can not work in a online way for conducting tasks in complex environments since it is trained with a batch manner which requires that all of the training samples should be given at the same time. In this paper, we propose an online version for GPS algorithm, which can learn policies incrementally without complete knowledge of initial positions for training. The experiments witness its efficacy on handling sequentially arriving training samples in a peg insertion task." @default.
- W2766702649 created "2017-11-10" @default.
- W2766702649 creator A5023214008 @default.
- W2766702649 creator A5026688050 @default.
- W2766702649 creator A5039337009 @default.
- W2766702649 creator A5056039500 @default.
- W2766702649 creator A5084878606 @default.
- W2766702649 date "2017-01-01" @default.
- W2766702649 modified "2023-09-25" @default.
- W2766702649 title "A Linear Online Guided Policy Search Algorithm" @default.
- W2766702649 cites W2051620263 @default.
- W2766702649 cites W2163533082 @default.
- W2766702649 cites W2529601334 @default.
- W2766702649 cites W3146846077 @default.
- W2766702649 doi "https://doi.org/10.1007/978-3-319-70139-4_44" @default.
- W2766702649 hasPublicationYear "2017" @default.
- W2766702649 type Work @default.
- W2766702649 sameAs 2766702649 @default.
- W2766702649 citedByCount "1" @default.
- W2766702649 countsByYear W27667026492021 @default.
- W2766702649 crossrefType "book-chapter" @default.
- W2766702649 hasAuthorship W2766702649A5023214008 @default.
- W2766702649 hasAuthorship W2766702649A5026688050 @default.
- W2766702649 hasAuthorship W2766702649A5039337009 @default.
- W2766702649 hasAuthorship W2766702649A5056039500 @default.
- W2766702649 hasAuthorship W2766702649A5084878606 @default.
- W2766702649 hasConcept C104317684 @default.
- W2766702649 hasConcept C11413529 @default.
- W2766702649 hasConcept C119857082 @default.
- W2766702649 hasConcept C154945302 @default.
- W2766702649 hasConcept C162324750 @default.
- W2766702649 hasConcept C185592680 @default.
- W2766702649 hasConcept C187736073 @default.
- W2766702649 hasConcept C199360897 @default.
- W2766702649 hasConcept C2776900844 @default.
- W2766702649 hasConcept C2777303404 @default.
- W2766702649 hasConcept C2780451532 @default.
- W2766702649 hasConcept C41008148 @default.
- W2766702649 hasConcept C50522688 @default.
- W2766702649 hasConcept C55493867 @default.
- W2766702649 hasConcept C60229501 @default.
- W2766702649 hasConcept C66746571 @default.
- W2766702649 hasConcept C76155785 @default.
- W2766702649 hasConcept C97541855 @default.
- W2766702649 hasConceptScore W2766702649C104317684 @default.
- W2766702649 hasConceptScore W2766702649C11413529 @default.
- W2766702649 hasConceptScore W2766702649C119857082 @default.
- W2766702649 hasConceptScore W2766702649C154945302 @default.
- W2766702649 hasConceptScore W2766702649C162324750 @default.
- W2766702649 hasConceptScore W2766702649C185592680 @default.
- W2766702649 hasConceptScore W2766702649C187736073 @default.
- W2766702649 hasConceptScore W2766702649C199360897 @default.
- W2766702649 hasConceptScore W2766702649C2776900844 @default.
- W2766702649 hasConceptScore W2766702649C2777303404 @default.
- W2766702649 hasConceptScore W2766702649C2780451532 @default.
- W2766702649 hasConceptScore W2766702649C41008148 @default.
- W2766702649 hasConceptScore W2766702649C50522688 @default.
- W2766702649 hasConceptScore W2766702649C55493867 @default.
- W2766702649 hasConceptScore W2766702649C60229501 @default.
- W2766702649 hasConceptScore W2766702649C66746571 @default.
- W2766702649 hasConceptScore W2766702649C76155785 @default.
- W2766702649 hasConceptScore W2766702649C97541855 @default.
- W2766702649 hasLocation W27667026491 @default.
- W2766702649 hasOpenAccess W2766702649 @default.
- W2766702649 hasPrimaryLocation W27667026491 @default.
- W2766702649 hasRelatedWork W1525257835 @default.
- W2766702649 hasRelatedWork W2097797606 @default.
- W2766702649 hasRelatedWork W2289410116 @default.
- W2766702649 hasRelatedWork W2528846071 @default.
- W2766702649 hasRelatedWork W2735325244 @default.
- W2766702649 hasRelatedWork W2739415903 @default.
- W2766702649 hasRelatedWork W286185234 @default.
- W2766702649 hasRelatedWork W2953981431 @default.
- W2766702649 hasRelatedWork W2963065769 @default.
- W2766702649 hasRelatedWork W2963704132 @default.
- W2766702649 hasRelatedWork W2995706821 @default.
- W2766702649 hasRelatedWork W2995931713 @default.
- W2766702649 hasRelatedWork W3005672216 @default.
- W2766702649 hasRelatedWork W3015731157 @default.
- W2766702649 hasRelatedWork W3036821294 @default.
- W2766702649 hasRelatedWork W3105184920 @default.
- W2766702649 hasRelatedWork W3130718980 @default.
- W2766702649 hasRelatedWork W3164371539 @default.
- W2766702649 hasRelatedWork W3208324826 @default.
- W2766702649 hasRelatedWork W3209208698 @default.
- W2766702649 isParatext "false" @default.
- W2766702649 isRetracted "false" @default.
- W2766702649 magId "2766702649" @default.
- W2766702649 workType "book-chapter" @default.