Matches in SemOpenAlex for { <https://semopenalex.org/work/W2770926475> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W2770926475 abstract "Deep Reinforcement learning enables autonomous robots to learn large repertories of behavioral skill with minimal human intervention. However, the applications of direct deep reinforcement learning have been restricted. For complicated robotic systems, these limitations result from high dimensional action space, high freedom of robotic system and high correlation between images. In this paper we introduce a new definition of action space and propose a double-task deep Q-Network with multiple views (DMDQN) based on double-DQN and dueling-DQN. For extension, we define multi-task model for more complex jobs. Moreover data augment policy is applied, which includes auto-sampling and action-overturn. The exploration policy is formed when DMDQN and data augment are combined. For robotic system's steady exploration, we designed the safety constraints according to working condition. Our experiments show that our double-task DQN with multiple views performs better than the single-task and single-view model. Combining our DMDQN and data augment, the robotic system can reach the object in an exploration way." @default.
- W2770926475 created "2017-12-04" @default.
- W2770926475 creator A5034994052 @default.
- W2770926475 creator A5055284422 @default.
- W2770926475 creator A5063471147 @default.
- W2770926475 creator A5078971977 @default.
- W2770926475 creator A5082857859 @default.
- W2770926475 creator A5089286262 @default.
- W2770926475 date "2017-10-01" @default.
- W2770926475 modified "2023-10-16" @default.
- W2770926475 title "Double-Task Deep Q-Learning with Multiple Views" @default.
- W2770926475 cites W1977655452 @default.
- W2770926475 cites W2042882799 @default.
- W2770926475 cites W2051620263 @default.
- W2770926475 cites W2100235553 @default.
- W2770926475 cites W2112796928 @default.
- W2770926475 cites W2125612430 @default.
- W2770926475 cites W2139053308 @default.
- W2770926475 cites W2145339207 @default.
- W2770926475 cites W2443711627 @default.
- W2770926475 doi "https://doi.org/10.1109/iccvw.2017.128" @default.
- W2770926475 hasPublicationYear "2017" @default.
- W2770926475 type Work @default.
- W2770926475 sameAs 2770926475 @default.
- W2770926475 citedByCount "4" @default.
- W2770926475 countsByYear W27709264752018 @default.
- W2770926475 countsByYear W27709264752019 @default.
- W2770926475 countsByYear W27709264752020 @default.
- W2770926475 countsByYear W27709264752022 @default.
- W2770926475 crossrefType "proceedings-article" @default.
- W2770926475 hasAuthorship W2770926475A5034994052 @default.
- W2770926475 hasAuthorship W2770926475A5055284422 @default.
- W2770926475 hasAuthorship W2770926475A5063471147 @default.
- W2770926475 hasAuthorship W2770926475A5078971977 @default.
- W2770926475 hasAuthorship W2770926475A5082857859 @default.
- W2770926475 hasAuthorship W2770926475A5089286262 @default.
- W2770926475 hasConcept C108583219 @default.
- W2770926475 hasConcept C127413603 @default.
- W2770926475 hasConcept C154945302 @default.
- W2770926475 hasConcept C201995342 @default.
- W2770926475 hasConcept C2780451532 @default.
- W2770926475 hasConcept C41008148 @default.
- W2770926475 hasConceptScore W2770926475C108583219 @default.
- W2770926475 hasConceptScore W2770926475C127413603 @default.
- W2770926475 hasConceptScore W2770926475C154945302 @default.
- W2770926475 hasConceptScore W2770926475C201995342 @default.
- W2770926475 hasConceptScore W2770926475C2780451532 @default.
- W2770926475 hasConceptScore W2770926475C41008148 @default.
- W2770926475 hasLocation W27709264751 @default.
- W2770926475 hasOpenAccess W2770926475 @default.
- W2770926475 hasPrimaryLocation W27709264751 @default.
- W2770926475 hasRelatedWork W2126887587 @default.
- W2770926475 hasRelatedWork W2731899572 @default.
- W2770926475 hasRelatedWork W2939353110 @default.
- W2770926475 hasRelatedWork W2941846814 @default.
- W2770926475 hasRelatedWork W2948658236 @default.
- W2770926475 hasRelatedWork W3009238340 @default.
- W2770926475 hasRelatedWork W3118091236 @default.
- W2770926475 hasRelatedWork W3164822677 @default.
- W2770926475 hasRelatedWork W3215138031 @default.
- W2770926475 hasRelatedWork W4230611425 @default.
- W2770926475 isParatext "false" @default.
- W2770926475 isRetracted "false" @default.
- W2770926475 magId "2770926475" @default.
- W2770926475 workType "article" @default.