FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313591595> ?p ?o ?g. }

• W4313591595 endingPage "161" @default.
• W4313591595 startingPage "144" @default.
• W4313591595 abstract "This paper proposes a FAst paRAllel and pipeliNE Q-learning accelerator (FARANE-Q) for a configurable Reinforcement Learning (RL) algorithm implemented in a System on Chip (SoC). The proposed work offers flexibility, configurability, and scalability while maintaining computation speed and accuracy to overcome the challenges of a dynamic environment and increasing complexity. The proposed method includes a Hardware/Software (HW/SW) design methodology for the SoC architecture to achieve flexibility. We also propose joint optimizations on the algorithm, architecture, and implementation to obtain optimum (high efficiency) performance, specifically in energy and area efficiency. Furthermore, we implemented the proposed design in a real-time Zynq Ultra96-V2 FPGA platform to evaluate the functionality with an actual use case of smart navigation. Experimental results confirm that the proposed accelerator FARANE-Q outperforms state-of-the-art works by achieving a throughput of up to 148.55 MSps. It corresponds to the energy efficiency of 1747.64 MSps/W per agent for 32-bit and 2424.33 MSps/W per agent for 16-bit FARANE-Q. Moreover, the proposed 16-bit FARANE-Q outperforms other related works by an improvement of at least <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$1.23times $ </tex-math></inline-formula> in energy efficiency. The designed system also maintains an error accuracy of less than 0.4% with optimized bit precision for more than eight fraction bits. The proposed FARANE-Q also offers a speed up of processing time up to <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$1795times $ </tex-math></inline-formula> compared to embedded SW computation executed on ARM Zynq processor and <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$280times $ </tex-math></inline-formula> of computation of full software executed on i7 processor. Hence, the proposed work has the potential to be used for smart navigation, robotic control, and predictive maintenance." @default.
• W4313591595 created "2023-01-06" @default.
• W4313591595 creator A5014109456 @default.
• W4313591595 creator A5019689855 @default.
• W4313591595 creator A5027261015 @default.
• W4313591595 creator A5038926636 @default.
• W4313591595 creator A5059864105 @default.
• W4313591595 date "2023-01-01" @default.
• W4313591595 modified "2023-10-18" @default.
• W4313591595 title "FARANE-Q: Fast Parallel and Pipeline Q-Learning Accelerator for Configurable Reinforcement Learning SoC" @default.
• W4313591595 cites W1646707810 @default.
• W4313591595 cites W1985031440 @default.
• W4313591595 cites W1996996894 @default.
• W4313591595 cites W2078895652 @default.
• W4313591595 cites W2087751887 @default.
• W4313591595 cites W2101786389 @default.
• W4313591595 cites W2575705757 @default.
• W4313591595 cites W2809148419 @default.
• W4313591595 cites W2889068523 @default.
• W4313591595 cites W2898035736 @default.
• W4313591595 cites W2904195769 @default.
• W4313591595 cites W2931767035 @default.
• W4313591595 cites W2945496227 @default.
• W4313591595 cites W2946943579 @default.
• W4313591595 cites W2949161920 @default.
• W4313591595 cites W2962684312 @default.
• W4313591595 cites W2963549123 @default.
• W4313591595 cites W2966691197 @default.
• W4313591595 cites W2967727187 @default.
• W4313591595 cites W2973184394 @default.
• W4313591595 cites W2998165854 @default.
• W4313591595 cites W3017007538 @default.
• W4313591595 cites W3046229513 @default.
• W4313591595 cites W3089396352 @default.
• W4313591595 cites W3090832565 @default.
• W4313591595 cites W3091592563 @default.
• W4313591595 cites W3102790199 @default.
• W4313591595 cites W3105381414 @default.
• W4313591595 cites W3111884232 @default.
• W4313591595 cites W3183385172 @default.
• W4313591595 cites W3202954520 @default.
• W4313591595 cites W3213742958 @default.
• W4313591595 cites W3216656735 @default.
• W4313591595 cites W4210397953 @default.
• W4313591595 cites W4231254085 @default.
• W4313591595 doi "https://doi.org/10.1109/access.2022.3232853" @default.
• W4313591595 hasPublicationYear "2023" @default.
• W4313591595 type Work @default.
• W4313591595 citedByCount "2" @default.
• W4313591595 countsByYear W43135915952023 @default.
• W4313591595 crossrefType "journal-article" @default.
• W4313591595 hasAuthorship W4313591595A5014109456 @default.
• W4313591595 hasAuthorship W4313591595A5019689855 @default.
• W4313591595 hasAuthorship W4313591595A5027261015 @default.
• W4313591595 hasAuthorship W4313591595A5038926636 @default.
• W4313591595 hasAuthorship W4313591595A5059864105 @default.
• W4313591595 hasBestOaLocation W43135915951 @default.
• W4313591595 hasConcept C105795698 @default.
• W4313591595 hasConcept C113775141 @default.
• W4313591595 hasConcept C118021083 @default.
• W4313591595 hasConcept C119599485 @default.
• W4313591595 hasConcept C127413603 @default.
• W4313591595 hasConcept C13164978 @default.
• W4313591595 hasConcept C149635348 @default.
• W4313591595 hasConcept C154945302 @default.
• W4313591595 hasConcept C173608175 @default.
• W4313591595 hasConcept C186370098 @default.
• W4313591595 hasConcept C188116033 @default.
• W4313591595 hasConcept C199360897 @default.
• W4313591595 hasConcept C2742236 @default.
• W4313591595 hasConcept C2780598303 @default.
• W4313591595 hasConcept C33923547 @default.
• W4313591595 hasConcept C41008148 @default.
• W4313591595 hasConcept C42935608 @default.
• W4313591595 hasConcept C43521106 @default.
• W4313591595 hasConcept C48044578 @default.
• W4313591595 hasConcept C77088390 @default.
• W4313591595 hasConcept C9390403 @default.
• W4313591595 hasConcept C97541855 @default.
• W4313591595 hasConceptScore W4313591595C105795698 @default.
• W4313591595 hasConceptScore W4313591595C113775141 @default.
• W4313591595 hasConceptScore W4313591595C118021083 @default.
• W4313591595 hasConceptScore W4313591595C119599485 @default.
• W4313591595 hasConceptScore W4313591595C127413603 @default.
• W4313591595 hasConceptScore W4313591595C13164978 @default.
• W4313591595 hasConceptScore W4313591595C149635348 @default.
• W4313591595 hasConceptScore W4313591595C154945302 @default.
• W4313591595 hasConceptScore W4313591595C173608175 @default.
• W4313591595 hasConceptScore W4313591595C186370098 @default.
• W4313591595 hasConceptScore W4313591595C188116033 @default.
• W4313591595 hasConceptScore W4313591595C199360897 @default.
• W4313591595 hasConceptScore W4313591595C2742236 @default.
• W4313591595 hasConceptScore W4313591595C2780598303 @default.
• W4313591595 hasConceptScore W4313591595C33923547 @default.
• W4313591595 hasConceptScore W4313591595C41008148 @default.
• W4313591595 hasConceptScore W4313591595C42935608 @default.
• W4313591595 hasConceptScore W4313591595C43521106 @default.
• W4313591595 hasConceptScore W4313591595C48044578 @default.

• next