Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360618223> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4360618223 abstract "Abstract Reinforcement learning is one of the most important methodologies in artificial intelligence and has achieved unprecedented success for addressing the fundamental decision-making tasks in various fields, including financial decisions, navigation, and robotic control tasks. However, the current reinforcement learning faces two well-recognized challenging problems, namely, trapping in the local optima and weak generalization, limiting its ability and performance to tackle complex and dynamic decision making tasks. Here, inspired by human intelligence, we present a new framework, called the emph{cognitive escape reinforcement learning} (CERL), that has the cognition escape module and the semantic cognition module, for avoiding local optima and achieving strong generalization. Moreover, we elaborate on CERL in a classical and complex decision-making task, namely, visual navigation. Extensive experiments demonstrate the efficacy of our proposed CERL framework. Its navigation performance is also remarkably superior to those of the state-of-the-art methods. Furthermore, it can achieve the highest navigation success rate, which is more than 6% higher than that of the best agent among the existing ones. The required path length is shortened by more than 29% and delivers real-time performance. Our presented reinforcement learning-based framework opens up a new direction for tackling future complex decision-making tasks rapidly and with high performance." @default.
- W4360618223 created "2023-03-24" @default.
- W4360618223 creator A5011900098 @default.
- W4360618223 creator A5032528268 @default.
- W4360618223 creator A5039378730 @default.
- W4360618223 creator A5042618993 @default.
- W4360618223 creator A5059248438 @default.
- W4360618223 creator A5089432787 @default.
- W4360618223 date "2023-03-23" @default.
- W4360618223 modified "2023-10-07" @default.
- W4360618223 title "Cognitive Escape Reinforcement Learning for Complex Decision Making" @default.
- W4360618223 doi "https://doi.org/10.21203/rs.3.rs-2661516/v1" @default.
- W4360618223 hasPublicationYear "2023" @default.
- W4360618223 type Work @default.
- W4360618223 citedByCount "0" @default.
- W4360618223 crossrefType "posted-content" @default.
- W4360618223 hasAuthorship W4360618223A5011900098 @default.
- W4360618223 hasAuthorship W4360618223A5032528268 @default.
- W4360618223 hasAuthorship W4360618223A5039378730 @default.
- W4360618223 hasAuthorship W4360618223A5042618993 @default.
- W4360618223 hasAuthorship W4360618223A5059248438 @default.
- W4360618223 hasAuthorship W4360618223A5089432787 @default.
- W4360618223 hasBestOaLocation W43606182231 @default.
- W4360618223 hasConcept C107457646 @default.
- W4360618223 hasConcept C119857082 @default.
- W4360618223 hasConcept C127413603 @default.
- W4360618223 hasConcept C134306372 @default.
- W4360618223 hasConcept C154945302 @default.
- W4360618223 hasConcept C15744967 @default.
- W4360618223 hasConcept C169760540 @default.
- W4360618223 hasConcept C169900460 @default.
- W4360618223 hasConcept C174988536 @default.
- W4360618223 hasConcept C177148314 @default.
- W4360618223 hasConcept C201995342 @default.
- W4360618223 hasConcept C2780451532 @default.
- W4360618223 hasConcept C33923547 @default.
- W4360618223 hasConcept C41008148 @default.
- W4360618223 hasConcept C97541855 @default.
- W4360618223 hasConceptScore W4360618223C107457646 @default.
- W4360618223 hasConceptScore W4360618223C119857082 @default.
- W4360618223 hasConceptScore W4360618223C127413603 @default.
- W4360618223 hasConceptScore W4360618223C134306372 @default.
- W4360618223 hasConceptScore W4360618223C154945302 @default.
- W4360618223 hasConceptScore W4360618223C15744967 @default.
- W4360618223 hasConceptScore W4360618223C169760540 @default.
- W4360618223 hasConceptScore W4360618223C169900460 @default.
- W4360618223 hasConceptScore W4360618223C174988536 @default.
- W4360618223 hasConceptScore W4360618223C177148314 @default.
- W4360618223 hasConceptScore W4360618223C201995342 @default.
- W4360618223 hasConceptScore W4360618223C2780451532 @default.
- W4360618223 hasConceptScore W4360618223C33923547 @default.
- W4360618223 hasConceptScore W4360618223C41008148 @default.
- W4360618223 hasConceptScore W4360618223C97541855 @default.
- W4360618223 hasLocation W43606182231 @default.
- W4360618223 hasOpenAccess W4360618223 @default.
- W4360618223 hasPrimaryLocation W43606182231 @default.
- W4360618223 hasRelatedWork W2055067456 @default.
- W4360618223 hasRelatedWork W2774891019 @default.
- W4360618223 hasRelatedWork W2951308022 @default.
- W4360618223 hasRelatedWork W2989932438 @default.
- W4360618223 hasRelatedWork W3022038857 @default.
- W4360618223 hasRelatedWork W4287626175 @default.
- W4360618223 hasRelatedWork W4288317198 @default.
- W4360618223 hasRelatedWork W4293469469 @default.
- W4360618223 hasRelatedWork W4302011254 @default.
- W4360618223 hasRelatedWork W4319083788 @default.
- W4360618223 isParatext "false" @default.
- W4360618223 isRetracted "false" @default.
- W4360618223 workType "article" @default.