FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2350784623> ?p ?o ?g. }

• W2350784623 abstract "This paper elaborates on the low learning efficiency in reinforcement learning due to improper generalization and random exploration policy under deterministic MDPS and proposes a hierarchical reinforcement learning algorithm based on system model.The algorithm adopts the two-lay structure.The low-layer selects the action by the greed policy and the high-layer detects and analyses the state value in the state space,guide the learning of low-layer,corrects the wrong the action selected by low-layer.The high-layer role includes the following: decrease the effect of state value convergence due to the improper generalization by setting the different learning parameters for the state value update in the state space;built the control rule in the state space and accelerate the learning rate by select action according to control rule;reduce the exploration of uncontrollable state space and non-optimal actions and limits the exploration concentrate on the controllable space.The proposed algorithm in this paper can achieve control quickly.Simulation results for the control of double inverted pendulum are presented to show the effectiveness of the proposed algorithm." @default.
• W2350784623 created "2016-06-24" @default.
• W2350784623 creator A5043754779 @default.
• W2350784623 date "2006-01-01" @default.
• W2350784623 modified "2023-09-23" @default.
• W2350784623 title "Hierarchical Reinforcement Learning Based on System Model" @default.
• W2350784623 hasPublicationYear "2006" @default.
• W2350784623 type Work @default.
• W2350784623 sameAs 2350784623 @default.
• W2350784623 citedByCount "0" @default.
• W2350784623 crossrefType "journal-article" @default.
• W2350784623 hasAuthorship W2350784623A5043754779 @default.
• W2350784623 hasConcept C102540577 @default.
• W2350784623 hasConcept C105795698 @default.
• W2350784623 hasConcept C111919701 @default.
• W2350784623 hasConcept C11413529 @default.
• W2350784623 hasConcept C117765406 @default.
• W2350784623 hasConcept C119857082 @default.
• W2350784623 hasConcept C121332964 @default.
• W2350784623 hasConcept C126255220 @default.
• W2350784623 hasConcept C134306372 @default.
• W2350784623 hasConcept C154945302 @default.
• W2350784623 hasConcept C158622935 @default.
• W2350784623 hasConcept C162324750 @default.
• W2350784623 hasConcept C177148314 @default.
• W2350784623 hasConcept C178790620 @default.
• W2350784623 hasConcept C185592680 @default.
• W2350784623 hasConcept C188116033 @default.
• W2350784623 hasConcept C192921069 @default.
• W2350784623 hasConcept C199190896 @default.
• W2350784623 hasConcept C2775924081 @default.
• W2350784623 hasConcept C2776291640 @default.
• W2350784623 hasConcept C2777303404 @default.
• W2350784623 hasConcept C2778572836 @default.
• W2350784623 hasConcept C2779227376 @default.
• W2350784623 hasConcept C2780791683 @default.
• W2350784623 hasConcept C33923547 @default.
• W2350784623 hasConcept C41008148 @default.
• W2350784623 hasConcept C48103436 @default.
• W2350784623 hasConcept C50522688 @default.
• W2350784623 hasConcept C62520636 @default.
• W2350784623 hasConcept C72434380 @default.
• W2350784623 hasConcept C8038995 @default.
• W2350784623 hasConcept C97541855 @default.
• W2350784623 hasConceptScore W2350784623C102540577 @default.
• W2350784623 hasConceptScore W2350784623C105795698 @default.
• W2350784623 hasConceptScore W2350784623C111919701 @default.
• W2350784623 hasConceptScore W2350784623C11413529 @default.
• W2350784623 hasConceptScore W2350784623C117765406 @default.
• W2350784623 hasConceptScore W2350784623C119857082 @default.
• W2350784623 hasConceptScore W2350784623C121332964 @default.
• W2350784623 hasConceptScore W2350784623C126255220 @default.
• W2350784623 hasConceptScore W2350784623C134306372 @default.
• W2350784623 hasConceptScore W2350784623C154945302 @default.
• W2350784623 hasConceptScore W2350784623C158622935 @default.
• W2350784623 hasConceptScore W2350784623C162324750 @default.
• W2350784623 hasConceptScore W2350784623C177148314 @default.
• W2350784623 hasConceptScore W2350784623C178790620 @default.
• W2350784623 hasConceptScore W2350784623C185592680 @default.
• W2350784623 hasConceptScore W2350784623C188116033 @default.
• W2350784623 hasConceptScore W2350784623C192921069 @default.
• W2350784623 hasConceptScore W2350784623C199190896 @default.
• W2350784623 hasConceptScore W2350784623C2775924081 @default.
• W2350784623 hasConceptScore W2350784623C2776291640 @default.
• W2350784623 hasConceptScore W2350784623C2777303404 @default.
• W2350784623 hasConceptScore W2350784623C2778572836 @default.
• W2350784623 hasConceptScore W2350784623C2779227376 @default.
• W2350784623 hasConceptScore W2350784623C2780791683 @default.
• W2350784623 hasConceptScore W2350784623C33923547 @default.
• W2350784623 hasConceptScore W2350784623C41008148 @default.
• W2350784623 hasConceptScore W2350784623C48103436 @default.
• W2350784623 hasConceptScore W2350784623C50522688 @default.
• W2350784623 hasConceptScore W2350784623C62520636 @default.
• W2350784623 hasConceptScore W2350784623C72434380 @default.
• W2350784623 hasConceptScore W2350784623C8038995 @default.
• W2350784623 hasConceptScore W2350784623C97541855 @default.
• W2350784623 hasLocation W23507846231 @default.
• W2350784623 hasOpenAccess W2350784623 @default.
• W2350784623 hasPrimaryLocation W23507846231 @default.
• W2350784623 hasRelatedWork W1525257835 @default.
• W2350784623 hasRelatedWork W1540471518 @default.
• W2350784623 hasRelatedWork W1624779897 @default.
• W2350784623 hasRelatedWork W1860787181 @default.
• W2350784623 hasRelatedWork W1997816436 @default.
• W2350784623 hasRelatedWork W2006115215 @default.
• W2350784623 hasRelatedWork W2061708029 @default.
• W2350784623 hasRelatedWork W2087104403 @default.
• W2350784623 hasRelatedWork W2129933049 @default.
• W2350784623 hasRelatedWork W225045806 @default.
• W2350784623 hasRelatedWork W2294374399 @default.
• W2350784623 hasRelatedWork W2347741501 @default.
• W2350784623 hasRelatedWork W2353658043 @default.
• W2350784623 hasRelatedWork W2357817307 @default.
• W2350784623 hasRelatedWork W2557003457 @default.
• W2350784623 hasRelatedWork W2782014475 @default.
• W2350784623 hasRelatedWork W2899685447 @default.
• W2350784623 hasRelatedWork W2435049346 @default.
• W2350784623 hasRelatedWork W3145769825 @default.
• W2350784623 hasRelatedWork W3169411365 @default.
• W2350784623 isParatext "false" @default.

• next