FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892979040> ?p ?o ?g. }

• W2892979040 endingPage "402" @default.
• W2892979040 startingPage "347" @default.
• W2892979040 abstract "Experience replay is a technique that allows off-policy reinforcement-learning methods to reuse past experiences. The stability and speed of convergence of reinforcement learning, as well as the eventual performance of the learned policy, are strongly dependent on the experiences being replayed. Which experiences are replayed depends on two important choices. The first is which and how many experiences to retain in the experience replay buffer. The second choice is how to sample the experiences that are to be replayed from that buffer. We propose new methods for the combined problem of experience retention and experience sampling. We refer to the combination as experience selection. We focus our investigation specifically on the control of physical systems, such as robots, where exploration is costly. To determine which experiences to keep and which to replay, we investigate different proxies for their immediate and long-term utility. These proxies include age, temporal difference error and the strength of the applied exploration noise. Since no currently available method works in all situations, we propose guidelines for using prior knowledge about the characteristics of the control problem at hand to choose the appropriate experience replay strategy." @default.
• W2892979040 created "2018-10-05" @default.
• W2892979040 creator A5008547992 @default.
• W2892979040 creator A5033347648 @default.
• W2892979040 creator A5035229829 @default.
• W2892979040 creator A5084264842 @default.
• W2892979040 date "2018-01-01" @default.
• W2892979040 modified "2023-09-26" @default.
• W2892979040 title "Experience selection in deep reinforcement learning for control" @default.
• W2892979040 cites W1481781224 @default.
• W2892979040 cites W1513016807 @default.
• W2892979040 cites W1520048352 @default.
• W2892979040 cites W1543614656 @default.
• W2892979040 cites W1576278180 @default.
• W2892979040 cites W172298727 @default.
• W2892979040 cites W1845972764 @default.
• W2892979040 cites W1977655452 @default.
• W2892979040 cites W1980035368 @default.
• W2892979040 cites W1998403501 @default.
• W2892979040 cites W2017957151 @default.
• W2892979040 cites W2019363670 @default.
• W2892979040 cites W2048226872 @default.
• W2892979040 cites W2103263764 @default.
• W2892979040 cites W2117897510 @default.
• W2892979040 cites W2119885577 @default.
• W2892979040 cites W2124695578 @default.
• W2892979040 cites W2139612737 @default.
• W2892979040 cites W2141559645 @default.
• W2892979040 cites W2145073242 @default.
• W2892979040 cites W2145339207 @default.
• W2892979040 cites W2159420891 @default.
• W2892979040 cites W2161388792 @default.
• W2892979040 cites W2162287622 @default.
• W2892979040 cites W2165150801 @default.
• W2892979040 cites W2166302491 @default.
• W2892979040 cites W2173248099 @default.
• W2892979040 cites W2174940656 @default.
• W2892979040 cites W2257979135 @default.
• W2892979040 cites W2266822037 @default.
• W2892979040 cites W2280163991 @default.
• W2892979040 cites W2296073425 @default.
• W2892979040 cites W2408978589 @default.
• W2892979040 cites W2547065907 @default.
• W2892979040 cites W2554120691 @default.
• W2892979040 cites W2554984891 @default.
• W2892979040 cites W2561666900 @default.
• W2892979040 cites W2582946978 @default.
• W2892979040 cites W2623491082 @default.
• W2892979040 cites W2766447205 @default.
• W2892979040 cites W2771101156 @default.
• W2892979040 cites W2783396564 @default.
• W2892979040 cites W2949801941 @default.
• W2892979040 cites W2950471160 @default.
• W2892979040 cites W2952629144 @default.
• W2892979040 cites W2962749646 @default.
• W2892979040 cites W2963477884 @default.
• W2892979040 cites W2964108562 @default.
• W2892979040 cites W2964121744 @default.
• W2892979040 cites W2964161785 @default.
• W2892979040 cites W3038264455 @default.
• W2892979040 cites W3148685027 @default.
• W2892979040 cites W753012316 @default.
• W2892979040 doi "https://doi.org/10.5555/3291125.3291134" @default.
• W2892979040 hasPublicationYear "2018" @default.
• W2892979040 type Work @default.
• W2892979040 sameAs 2892979040 @default.
• W2892979040 citedByCount "14" @default.
• W2892979040 countsByYear W28929790402018 @default.
• W2892979040 countsByYear W28929790402019 @default.
• W2892979040 countsByYear W28929790402020 @default.
• W2892979040 countsByYear W28929790402021 @default.
• W2892979040 countsByYear W28929790402022 @default.
• W2892979040 crossrefType "journal-article" @default.
• W2892979040 hasAuthorship W2892979040A5008547992 @default.
• W2892979040 hasAuthorship W2892979040A5033347648 @default.
• W2892979040 hasAuthorship W2892979040A5035229829 @default.
• W2892979040 hasAuthorship W2892979040A5084264842 @default.
• W2892979040 hasConcept C112972136 @default.
• W2892979040 hasConcept C119857082 @default.
• W2892979040 hasConcept C120665830 @default.
• W2892979040 hasConcept C121332964 @default.
• W2892979040 hasConcept C127413603 @default.
• W2892979040 hasConcept C154945302 @default.
• W2892979040 hasConcept C162324750 @default.
• W2892979040 hasConcept C185592680 @default.
• W2892979040 hasConcept C192209626 @default.
• W2892979040 hasConcept C198531522 @default.
• W2892979040 hasConcept C206588197 @default.
• W2892979040 hasConcept C2775924081 @default.
• W2892979040 hasConcept C2777303404 @default.
• W2892979040 hasConcept C41008148 @default.
• W2892979040 hasConcept C43617362 @default.
• W2892979040 hasConcept C50522688 @default.
• W2892979040 hasConcept C548081761 @default.
• W2892979040 hasConcept C81917197 @default.
• W2892979040 hasConcept C97541855 @default.
• W2892979040 hasConceptScore W2892979040C112972136 @default.
• W2892979040 hasConceptScore W2892979040C119857082 @default.

• next