FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2779040504> ?p ?o ?g. }

• W2779040504 abstract "Reinforcement learning (RL) algorithms involve the deep nesting of distinct components, where each component typically exhibits opportunities for distributed computation. Current RL libraries offer parallelism at the level of the entire program, coupling all the components together and making existing implementations difficult to extend, combine, and reuse. We argue for building composable RL components by encapsulating parallelism and resource requirements within individual components, which can be achieved by building on top of a flexible task-based programming model. We demonstrate this principle by building Ray RLLib on top of Ray and show that we can implement a wide range of state-of-the-art algorithms by composing and reusing a handful of standard components. This composability does not come at the cost of performance --- in our experiments, RLLib matches or exceeds the performance of highly optimized reference implementations. Ray RLLib is available as part of Ray at this https URL" @default.
• W2779040504 created "2018-01-05" @default.
• W2779040504 creator A5034807958 @default.
• W2779040504 creator A5041920173 @default.
• W2779040504 creator A5050342525 @default.
• W2779040504 creator A5054259891 @default.
• W2779040504 creator A5064891668 @default.
• W2779040504 creator A5072427753 @default.
• W2779040504 creator A5073588383 @default.
• W2779040504 creator A5075667645 @default.
• W2779040504 date "2017-12-26" @default.
• W2779040504 modified "2023-09-28" @default.
• W2779040504 title "Ray RLLib: A Composable and Scalable Reinforcement Learning Library" @default.
• W2779040504 cites W1658008008 @default.
• W2779040504 cites W1981420413 @default.
• W2779040504 cites W1982063824 @default.
• W2779040504 cites W2081612620 @default.
• W2779040504 cites W2083842231 @default.
• W2779040504 cites W2101677491 @default.
• W2779040504 cites W2114271627 @default.
• W2779040504 cites W2119717200 @default.
• W2779040504 cites W2121863487 @default.
• W2779040504 cites W2145339207 @default.
• W2779040504 cites W2155968351 @default.
• W2779040504 cites W2173213060 @default.
• W2779040504 cites W2173248099 @default.
• W2779040504 cites W2173564293 @default.
• W2779040504 cites W2186615578 @default.
• W2779040504 cites W2201581102 @default.
• W2779040504 cites W2242902128 @default.
• W2779040504 cites W2257979135 @default.
• W2779040504 cites W2271840356 @default.
• W2779040504 cites W2342662072 @default.
• W2779040504 cites W2395575420 @default.
• W2779040504 cites W2556958149 @default.
• W2779040504 cites W2585388895 @default.
• W2779040504 cites W2596367596 @default.
• W2779040504 cites W2602275733 @default.
• W2779040504 cites W2604283518 @default.
• W2779040504 cites W2619307294 @default.
• W2779040504 cites W2621550233 @default.
• W2779040504 cites W2623431351 @default.
• W2779040504 cites W2732547613 @default.
• W2779040504 cites W2733961795 @default.
• W2779040504 cites W2735347808 @default.
• W2779040504 cites W2736601468 @default.
• W2779040504 cites W2738675347 @default.
• W2779040504 cites W2739473244 @default.
• W2779040504 cites W2756071177 @default.
• W2779040504 cites W2756196406 @default.
• W2779040504 cites W2761873684 @default.
• W2779040504 cites W2766447205 @default.
• W2779040504 cites W2780624097 @default.
• W2779040504 cites W2786036274 @default.
• W2779040504 cites W2786928559 @default.
• W2779040504 cites W2899771611 @default.
• W2779040504 cites W2949608212 @default.
• W2779040504 cites W2950094539 @default.
• W2779040504 cites W2950492145 @default.
• W2779040504 cites W2950872548 @default.
• W2779040504 cites W2963184621 @default.
• W2779040504 cites W2963571817 @default.
• W2779040504 cites W2964043796 @default.
• W2779040504 cites W2770298516 @default.
• W2779040504 hasPublicationYear "2017" @default.
• W2779040504 type Work @default.
• W2779040504 sameAs 2779040504 @default.
• W2779040504 citedByCount "43" @default.
• W2779040504 countsByYear W27790405042017 @default.
• W2779040504 countsByYear W27790405042018 @default.
• W2779040504 countsByYear W27790405042019 @default.
• W2779040504 countsByYear W27790405042020 @default.
• W2779040504 countsByYear W27790405042021 @default.
• W2779040504 countsByYear W27790405042022 @default.
• W2779040504 crossrefType "posted-content" @default.
• W2779040504 hasAuthorship W2779040504A5034807958 @default.
• W2779040504 hasAuthorship W2779040504A5041920173 @default.
• W2779040504 hasAuthorship W2779040504A5050342525 @default.
• W2779040504 hasAuthorship W2779040504A5054259891 @default.
• W2779040504 hasAuthorship W2779040504A5064891668 @default.
• W2779040504 hasAuthorship W2779040504A5072427753 @default.
• W2779040504 hasAuthorship W2779040504A5073588383 @default.
• W2779040504 hasAuthorship W2779040504A5075667645 @default.
• W2779040504 hasConcept C111919701 @default.
• W2779040504 hasConcept C118524514 @default.
• W2779040504 hasConcept C120314980 @default.
• W2779040504 hasConcept C121332964 @default.
• W2779040504 hasConcept C127413603 @default.
• W2779040504 hasConcept C146978453 @default.
• W2779040504 hasConcept C154945302 @default.
• W2779040504 hasConcept C168167062 @default.
• W2779040504 hasConcept C173608175 @default.
• W2779040504 hasConcept C199360897 @default.
• W2779040504 hasConcept C201995342 @default.
• W2779040504 hasConcept C204323151 @default.
• W2779040504 hasConcept C206588197 @default.
• W2779040504 hasConcept C26713055 @default.
• W2779040504 hasConcept C2776937656 @default.
• W2779040504 hasConcept C2778814252 @default.
• W2779040504 hasConcept C2780451532 @default.

• next