FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962744619> ?p ?o ?g. }

• W2962744619 endingPage "255" @default.
• W2962744619 startingPage "243" @default.
• W2962744619 abstract "Autonomous learning is a crucially important capability of intelligent robots. As one of the most fashionable machine learning techniques, the reinforcement learning (RL) enables an agent taking an optimized action by interacting with the environment so as to maximize some notion of cumulative reward. In this paper, an improved RL algorithm, named as the KT-HA-Q(λ) algorithm, is proposed by resorting to the knowledge transfer of source domain. First, a BP neural network and a liner sensor network are skillfully constructed to perform the knowledge transfer of source task for weight initialization in target task, and the knowledge transfer on actions of case base obtained by source domain, respectively. Then, the novel case base expansion and progressive forgetting criterion, which realize the balance between new experience via online learning and historical experience in the case base, are developed to enhance the learning efficiency and the learning rate. Furthermore, an improved heuristic function is proposed by replacing the action traditionally obtained via a selection strategy by the experience action. This function acts as a crucial role for both the best action selection and its Q value calculation. Finally, the proposed algorithm is utilized in the hill-climbing experiment of unmanned vehicles under a complex 3D scene by transferring the knowledge obtained in a 2D scene. The results of contrast experiments verified the advantages and effectiveness of the proposed algorithm." @default.
• W2962744619 created "2019-07-30" @default.
• W2962744619 creator A5002188950 @default.
• W2962744619 creator A5046519432 @default.
• W2962744619 creator A5056447198 @default.
• W2962744619 creator A5083723742 @default.
• W2962744619 date "2019-10-01" @default.
• W2962744619 modified "2023-10-14" @default.
• W2962744619 title "An improved reinforcement learning algorithm based on knowledge transfer and applications in autonomous vehicles" @default.
• W2962744619 cites W1530174427 @default.
• W2962744619 cites W1973627122 @default.
• W2962744619 cites W1986014385 @default.
• W2962744619 cites W2002334697 @default.
• W2962744619 cites W2020573190 @default.
• W2962744619 cites W2021247827 @default.
• W2962744619 cites W2036103676 @default.
• W2962744619 cites W2056584142 @default.
• W2962744619 cites W2073320424 @default.
• W2962744619 cites W2079206596 @default.
• W2962744619 cites W2096600060 @default.
• W2962744619 cites W2113913482 @default.
• W2962744619 cites W2126385963 @default.
• W2962744619 cites W2130935956 @default.
• W2962744619 cites W2145339207 @default.
• W2962744619 cites W2165698076 @default.
• W2962744619 cites W2259258048 @default.
• W2962744619 cites W2634239194 @default.
• W2962744619 cites W2780033408 @default.
• W2962744619 cites W2789561271 @default.
• W2962744619 cites W2790702239 @default.
• W2962744619 cites W2799479426 @default.
• W2962744619 cites W2803459852 @default.
• W2962744619 cites W2885108836 @default.
• W2962744619 cites W2922520136 @default.
• W2962744619 cites W3103256699 @default.
• W2962744619 cites W605348272 @default.
• W2962744619 cites W851745253 @default.
• W2962744619 doi "https://doi.org/10.1016/j.neucom.2019.06.067" @default.
• W2962744619 hasPublicationYear "2019" @default.
• W2962744619 type Work @default.
• W2962744619 sameAs 2962744619 @default.
• W2962744619 citedByCount "12" @default.
• W2962744619 countsByYear W29627446192020 @default.
• W2962744619 countsByYear W29627446192021 @default.
• W2962744619 countsByYear W29627446192022 @default.
• W2962744619 countsByYear W29627446192023 @default.
• W2962744619 crossrefType "journal-article" @default.
• W2962744619 hasAuthorship W2962744619A5002188950 @default.
• W2962744619 hasAuthorship W2962744619A5046519432 @default.
• W2962744619 hasAuthorship W2962744619A5056447198 @default.
• W2962744619 hasAuthorship W2962744619A5083723742 @default.
• W2962744619 hasConcept C114466953 @default.
• W2962744619 hasConcept C119857082 @default.
• W2962744619 hasConcept C121332964 @default.
• W2962744619 hasConcept C127413603 @default.
• W2962744619 hasConcept C134306372 @default.
• W2962744619 hasConcept C135450995 @default.
• W2962744619 hasConcept C138885662 @default.
• W2962744619 hasConcept C14036430 @default.
• W2962744619 hasConcept C150899416 @default.
• W2962744619 hasConcept C154945302 @default.
• W2962744619 hasConcept C166109690 @default.
• W2962744619 hasConcept C169760540 @default.
• W2962744619 hasConcept C173801870 @default.
• W2962744619 hasConcept C188888258 @default.
• W2962744619 hasConcept C199360897 @default.
• W2962744619 hasConcept C19966478 @default.
• W2962744619 hasConcept C201995342 @default.
• W2962744619 hasConcept C207685749 @default.
• W2962744619 hasConcept C26760741 @default.
• W2962744619 hasConcept C2780451532 @default.
• W2962744619 hasConcept C2780791683 @default.
• W2962744619 hasConcept C33923547 @default.
• W2962744619 hasConcept C36503486 @default.
• W2962744619 hasConcept C41008148 @default.
• W2962744619 hasConcept C41895202 @default.
• W2962744619 hasConcept C4554734 @default.
• W2962744619 hasConcept C50644808 @default.
• W2962744619 hasConcept C62520636 @default.
• W2962744619 hasConcept C7149132 @default.
• W2962744619 hasConcept C77075516 @default.
• W2962744619 hasConcept C78458016 @default.
• W2962744619 hasConcept C81917197 @default.
• W2962744619 hasConcept C86803240 @default.
• W2962744619 hasConcept C90509273 @default.
• W2962744619 hasConcept C97541855 @default.
• W2962744619 hasConceptScore W2962744619C114466953 @default.
• W2962744619 hasConceptScore W2962744619C119857082 @default.
• W2962744619 hasConceptScore W2962744619C121332964 @default.
• W2962744619 hasConceptScore W2962744619C127413603 @default.
• W2962744619 hasConceptScore W2962744619C134306372 @default.
• W2962744619 hasConceptScore W2962744619C135450995 @default.
• W2962744619 hasConceptScore W2962744619C138885662 @default.
• W2962744619 hasConceptScore W2962744619C14036430 @default.
• W2962744619 hasConceptScore W2962744619C150899416 @default.
• W2962744619 hasConceptScore W2962744619C154945302 @default.
• W2962744619 hasConceptScore W2962744619C166109690 @default.
• W2962744619 hasConceptScore W2962744619C169760540 @default.

• next