Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385978583> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4385978583 endingPage "3508" @default.
- W4385978583 startingPage "3508" @default.
- W4385978583 abstract "In deep reinforcement learning, agent exploration still has certain limitations, while low efficiency exploration further leads to the problem of low sample efficiency. In order to solve the exploration dilemma caused by white noise interference and the separation derailment problem in the environment, we present an innovative approach by introducing an intricately honed feature extraction module to harness the predictive errors, generate intrinsic rewards, and use an ancillary agent training paradigm that effectively solves the above problems and significantly enhances the agent’s capacity for comprehensive exploration within environments characterized by sparse reward distribution. The efficacy of the optimized feature extraction module is substantiated through comparative experiments conducted within the arduous exploration problem scenarios often employed in reinforcement learning investigations. Furthermore, a comprehensive performance analysis of our method is executed within the esteemed Atari 2600 experimental setting, yielding noteworthy advancements in performance and showcasing the attainment of superior outcomes in six selected experimental environments." @default.
- W4385978583 created "2023-08-19" @default.
- W4385978583 creator A5006092039 @default.
- W4385978583 creator A5077717253 @default.
- W4385978583 creator A5083147296 @default.
- W4385978583 creator A5091671160 @default.
- W4385978583 date "2023-08-18" @default.
- W4385978583 modified "2023-10-14" @default.
- W4385978583 title "Optimized Feature Extraction for Sample Efficient Deep Reinforcement Learning" @default.
- W4385978583 cites W1988526405 @default.
- W4385978583 cites W2009551863 @default.
- W4385978583 cites W2257979135 @default.
- W4385978583 cites W2761873684 @default.
- W4385978583 cites W2766447205 @default.
- W4385978583 cites W2962937819 @default.
- W4385978583 cites W2963523627 @default.
- W4385978583 cites W2982316857 @default.
- W4385978583 cites W2990747716 @default.
- W4385978583 cites W2997289589 @default.
- W4385978583 cites W3013624091 @default.
- W4385978583 cites W3103780890 @default.
- W4385978583 cites W3129322645 @default.
- W4385978583 cites W4205563028 @default.
- W4385978583 cites W4220747123 @default.
- W4385978583 doi "https://doi.org/10.3390/electronics12163508" @default.
- W4385978583 hasPublicationYear "2023" @default.
- W4385978583 type Work @default.
- W4385978583 citedByCount "0" @default.
- W4385978583 crossrefType "journal-article" @default.
- W4385978583 hasAuthorship W4385978583A5006092039 @default.
- W4385978583 hasAuthorship W4385978583A5077717253 @default.
- W4385978583 hasAuthorship W4385978583A5083147296 @default.
- W4385978583 hasAuthorship W4385978583A5091671160 @default.
- W4385978583 hasBestOaLocation W43859785831 @default.
- W4385978583 hasConcept C119857082 @default.
- W4385978583 hasConcept C138885662 @default.
- W4385978583 hasConcept C154945302 @default.
- W4385978583 hasConcept C185592680 @default.
- W4385978583 hasConcept C198531522 @default.
- W4385978583 hasConcept C2776401178 @default.
- W4385978583 hasConcept C41008148 @default.
- W4385978583 hasConcept C41895202 @default.
- W4385978583 hasConcept C43617362 @default.
- W4385978583 hasConcept C52622490 @default.
- W4385978583 hasConcept C97541855 @default.
- W4385978583 hasConceptScore W4385978583C119857082 @default.
- W4385978583 hasConceptScore W4385978583C138885662 @default.
- W4385978583 hasConceptScore W4385978583C154945302 @default.
- W4385978583 hasConceptScore W4385978583C185592680 @default.
- W4385978583 hasConceptScore W4385978583C198531522 @default.
- W4385978583 hasConceptScore W4385978583C2776401178 @default.
- W4385978583 hasConceptScore W4385978583C41008148 @default.
- W4385978583 hasConceptScore W4385978583C41895202 @default.
- W4385978583 hasConceptScore W4385978583C43617362 @default.
- W4385978583 hasConceptScore W4385978583C52622490 @default.
- W4385978583 hasConceptScore W4385978583C97541855 @default.
- W4385978583 hasFunder F4320321001 @default.
- W4385978583 hasIssue "16" @default.
- W4385978583 hasLocation W43859785831 @default.
- W4385978583 hasOpenAccess W4385978583 @default.
- W4385978583 hasPrimaryLocation W43859785831 @default.
- W4385978583 hasRelatedWork W2024136090 @default.
- W4385978583 hasRelatedWork W2031695474 @default.
- W4385978583 hasRelatedWork W2138720691 @default.
- W4385978583 hasRelatedWork W2586732548 @default.
- W4385978583 hasRelatedWork W2964765435 @default.
- W4385978583 hasRelatedWork W3049728571 @default.
- W4385978583 hasRelatedWork W4306904969 @default.
- W4385978583 hasRelatedWork W4362501864 @default.
- W4385978583 hasRelatedWork W4380318855 @default.
- W4385978583 hasRelatedWork W2585069576 @default.
- W4385978583 hasVolume "12" @default.
- W4385978583 isParatext "false" @default.
- W4385978583 isRetracted "false" @default.
- W4385978583 workType "article" @default.