Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895095307> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2895095307 endingPage "012063" @default.
- W2895095307 startingPage "012063" @default.
- W2895095307 abstract "In this paper, aiming at the problems of 2-DOF horizontal motion control with high precision for autonomous underwater vehicle(AUV) trajectory tracking tasks, deep reinforcement learning controllers are applied to these conditions. These control problems are considered as a POMDP (Partially Observable Markov Decision Process). Model-free reinforcement learning(RL) algorithms for continuous control mission based on Deterministic Policy Gradient(DPG) allows robots learn from received delayed rewards when interacting with environments. Recurrent neural networks LSTM (Long Short-Term Memory) are involved into the reinforcement learning algorithm. Through this deep reinforcement learning algorithm, AUVs learn from sequences of dynamic information. The horizontal trajectory tracking tasks are described by LOS method and the motion control are idealized as a SISO model. Tanh-estimators are presented as data normalization. Moreover, AUV horizontal trajectory tracking and motion control simulation results demonstrate this algorithm gets better accuracy compared with the PID method and other non-recurrent methods. Efforts show the efficiency and effectiveness of the improved deep reinforcement learning algorithm." @default.
- W2895095307 created "2018-10-12" @default.
- W2895095307 creator A5015833949 @default.
- W2895095307 creator A5027072664 @default.
- W2895095307 creator A5070772177 @default.
- W2895095307 date "2018-10-01" @default.
- W2895095307 modified "2023-09-24" @default.
- W2895095307 title "Model-Free Recurrent Reinforcement Learning for AUV Horizontal Control" @default.
- W2895095307 cites W1949804828 @default.
- W2895095307 cites W2087963019 @default.
- W2895095307 cites W2105551637 @default.
- W2895095307 cites W2150355110 @default.
- W2895095307 cites W2899291427 @default.
- W2895095307 doi "https://doi.org/10.1088/1757-899x/428/1/012063" @default.
- W2895095307 hasPublicationYear "2018" @default.
- W2895095307 type Work @default.
- W2895095307 sameAs 2895095307 @default.
- W2895095307 citedByCount "4" @default.
- W2895095307 countsByYear W28950953072020 @default.
- W2895095307 countsByYear W28950953072021 @default.
- W2895095307 countsByYear W28950953072022 @default.
- W2895095307 crossrefType "journal-article" @default.
- W2895095307 hasAuthorship W2895095307A5015833949 @default.
- W2895095307 hasAuthorship W2895095307A5027072664 @default.
- W2895095307 hasAuthorship W2895095307A5070772177 @default.
- W2895095307 hasBestOaLocation W28950953071 @default.
- W2895095307 hasConcept C104114177 @default.
- W2895095307 hasConcept C121332964 @default.
- W2895095307 hasConcept C127413603 @default.
- W2895095307 hasConcept C1276947 @default.
- W2895095307 hasConcept C13662910 @default.
- W2895095307 hasConcept C136886441 @default.
- W2895095307 hasConcept C144024400 @default.
- W2895095307 hasConcept C145565327 @default.
- W2895095307 hasConcept C146978453 @default.
- W2895095307 hasConcept C154945302 @default.
- W2895095307 hasConcept C15744967 @default.
- W2895095307 hasConcept C19165224 @default.
- W2895095307 hasConcept C19417346 @default.
- W2895095307 hasConcept C2775924081 @default.
- W2895095307 hasConcept C2775936607 @default.
- W2895095307 hasConcept C2776937971 @default.
- W2895095307 hasConcept C41008148 @default.
- W2895095307 hasConcept C47446073 @default.
- W2895095307 hasConcept C90509273 @default.
- W2895095307 hasConcept C97541855 @default.
- W2895095307 hasConceptScore W2895095307C104114177 @default.
- W2895095307 hasConceptScore W2895095307C121332964 @default.
- W2895095307 hasConceptScore W2895095307C127413603 @default.
- W2895095307 hasConceptScore W2895095307C1276947 @default.
- W2895095307 hasConceptScore W2895095307C13662910 @default.
- W2895095307 hasConceptScore W2895095307C136886441 @default.
- W2895095307 hasConceptScore W2895095307C144024400 @default.
- W2895095307 hasConceptScore W2895095307C145565327 @default.
- W2895095307 hasConceptScore W2895095307C146978453 @default.
- W2895095307 hasConceptScore W2895095307C154945302 @default.
- W2895095307 hasConceptScore W2895095307C15744967 @default.
- W2895095307 hasConceptScore W2895095307C19165224 @default.
- W2895095307 hasConceptScore W2895095307C19417346 @default.
- W2895095307 hasConceptScore W2895095307C2775924081 @default.
- W2895095307 hasConceptScore W2895095307C2775936607 @default.
- W2895095307 hasConceptScore W2895095307C2776937971 @default.
- W2895095307 hasConceptScore W2895095307C41008148 @default.
- W2895095307 hasConceptScore W2895095307C47446073 @default.
- W2895095307 hasConceptScore W2895095307C90509273 @default.
- W2895095307 hasConceptScore W2895095307C97541855 @default.
- W2895095307 hasLocation W28950953071 @default.
- W2895095307 hasOpenAccess W2895095307 @default.
- W2895095307 hasPrimaryLocation W28950953071 @default.
- W2895095307 hasRelatedWork W2054035906 @default.
- W2895095307 hasRelatedWork W2139667288 @default.
- W2895095307 hasRelatedWork W2735800644 @default.
- W2895095307 hasRelatedWork W2792333933 @default.
- W2895095307 hasRelatedWork W2984863875 @default.
- W2895095307 hasRelatedWork W3084370450 @default.
- W2895095307 hasRelatedWork W3093235801 @default.
- W2895095307 hasRelatedWork W3156861611 @default.
- W2895095307 hasRelatedWork W4205591831 @default.
- W2895095307 hasRelatedWork W4363649607 @default.
- W2895095307 hasVolume "428" @default.
- W2895095307 isParatext "false" @default.
- W2895095307 isRetracted "false" @default.
- W2895095307 magId "2895095307" @default.
- W2895095307 workType "article" @default.