Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386875978> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4386875978 abstract "In Reinforcement Learning, the trade-off between exploration and exploitation poses a complex challenge for achieving efficient learning from limited samples. While recent works have been effective in leveraging past experiences for policy updates, they often overlook the potential of reusing past experiences for data collection. Independent of the underlying RL algorithm, we introduce the concept of a Contrastive Initial State Buffer, which strategically selects states from past experiences and uses them to initialize the agent in the environment in order to guide it toward more informative states. We validate our approach on two complex robotic tasks without relying on any prior information about the environment: (i) locomotion of a quadruped robot traversing challenging terrains and (ii) a quadcopter drone racing through a track. The experimental results show that our initial state buffer achieves higher task performance than the nominal baseline while also speeding up training convergence." @default.
- W4386875978 created "2023-09-20" @default.
- W4386875978 creator A5045918081 @default.
- W4386875978 creator A5057116316 @default.
- W4386875978 creator A5085971429 @default.
- W4386875978 date "2023-09-18" @default.
- W4386875978 modified "2023-09-29" @default.
- W4386875978 title "Contrastive Initial State Buffer for Reinforcement Learning" @default.
- W4386875978 doi "https://doi.org/10.48550/arxiv.2309.09752" @default.
- W4386875978 hasPublicationYear "2023" @default.
- W4386875978 type Work @default.
- W4386875978 citedByCount "0" @default.
- W4386875978 crossrefType "posted-content" @default.
- W4386875978 hasAuthorship W4386875978A5045918081 @default.
- W4386875978 hasAuthorship W4386875978A5057116316 @default.
- W4386875978 hasAuthorship W4386875978A5085971429 @default.
- W4386875978 hasBestOaLocation W43868759781 @default.
- W4386875978 hasConcept C107457646 @default.
- W4386875978 hasConcept C111368507 @default.
- W4386875978 hasConcept C11413529 @default.
- W4386875978 hasConcept C119857082 @default.
- W4386875978 hasConcept C12725497 @default.
- W4386875978 hasConcept C127313418 @default.
- W4386875978 hasConcept C127413603 @default.
- W4386875978 hasConcept C13280743 @default.
- W4386875978 hasConcept C146978453 @default.
- W4386875978 hasConcept C154945302 @default.
- W4386875978 hasConcept C161840515 @default.
- W4386875978 hasConcept C162324750 @default.
- W4386875978 hasConcept C176809094 @default.
- W4386875978 hasConcept C18903297 @default.
- W4386875978 hasConcept C201995342 @default.
- W4386875978 hasConcept C205649164 @default.
- W4386875978 hasConcept C206588197 @default.
- W4386875978 hasConcept C2777303404 @default.
- W4386875978 hasConcept C2779199153 @default.
- W4386875978 hasConcept C2780451532 @default.
- W4386875978 hasConcept C41008148 @default.
- W4386875978 hasConcept C48103436 @default.
- W4386875978 hasConcept C50522688 @default.
- W4386875978 hasConcept C54355233 @default.
- W4386875978 hasConcept C548081761 @default.
- W4386875978 hasConcept C59519942 @default.
- W4386875978 hasConcept C86803240 @default.
- W4386875978 hasConcept C90509273 @default.
- W4386875978 hasConcept C97541855 @default.
- W4386875978 hasConceptScore W4386875978C107457646 @default.
- W4386875978 hasConceptScore W4386875978C111368507 @default.
- W4386875978 hasConceptScore W4386875978C11413529 @default.
- W4386875978 hasConceptScore W4386875978C119857082 @default.
- W4386875978 hasConceptScore W4386875978C12725497 @default.
- W4386875978 hasConceptScore W4386875978C127313418 @default.
- W4386875978 hasConceptScore W4386875978C127413603 @default.
- W4386875978 hasConceptScore W4386875978C13280743 @default.
- W4386875978 hasConceptScore W4386875978C146978453 @default.
- W4386875978 hasConceptScore W4386875978C154945302 @default.
- W4386875978 hasConceptScore W4386875978C161840515 @default.
- W4386875978 hasConceptScore W4386875978C162324750 @default.
- W4386875978 hasConceptScore W4386875978C176809094 @default.
- W4386875978 hasConceptScore W4386875978C18903297 @default.
- W4386875978 hasConceptScore W4386875978C201995342 @default.
- W4386875978 hasConceptScore W4386875978C205649164 @default.
- W4386875978 hasConceptScore W4386875978C206588197 @default.
- W4386875978 hasConceptScore W4386875978C2777303404 @default.
- W4386875978 hasConceptScore W4386875978C2779199153 @default.
- W4386875978 hasConceptScore W4386875978C2780451532 @default.
- W4386875978 hasConceptScore W4386875978C41008148 @default.
- W4386875978 hasConceptScore W4386875978C48103436 @default.
- W4386875978 hasConceptScore W4386875978C50522688 @default.
- W4386875978 hasConceptScore W4386875978C54355233 @default.
- W4386875978 hasConceptScore W4386875978C548081761 @default.
- W4386875978 hasConceptScore W4386875978C59519942 @default.
- W4386875978 hasConceptScore W4386875978C86803240 @default.
- W4386875978 hasConceptScore W4386875978C90509273 @default.
- W4386875978 hasConceptScore W4386875978C97541855 @default.
- W4386875978 hasLocation W43868759781 @default.
- W4386875978 hasOpenAccess W4386875978 @default.
- W4386875978 hasPrimaryLocation W43868759781 @default.
- W4386875978 hasRelatedWork W2120408833 @default.
- W4386875978 hasRelatedWork W2154871086 @default.
- W4386875978 hasRelatedWork W2166802441 @default.
- W4386875978 hasRelatedWork W2906841975 @default.
- W4386875978 hasRelatedWork W3027249399 @default.
- W4386875978 hasRelatedWork W3033068628 @default.
- W4386875978 hasRelatedWork W3089721783 @default.
- W4386875978 hasRelatedWork W3213331859 @default.
- W4386875978 hasRelatedWork W4226458444 @default.
- W4386875978 hasRelatedWork W4385328001 @default.
- W4386875978 isParatext "false" @default.
- W4386875978 isRetracted "false" @default.
- W4386875978 workType "article" @default.