Matches in SemOpenAlex for { <https://semopenalex.org/work/W2171700688> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2171700688 abstract "Q-Learning is a popular reinforcement learning algorithm which has been widely used in stochastic control applications. The bottleneck of applying tabular form Q-learning in reinforcement learning problems with large scale or high dimensional action sets is the considerable delays caused by action selection and value function updates. In this paper, we present a novel hardware architecture that significantly reduces the delays. Moreover, we formulate the Q-learning algorithm in cases of observation and action delays and provide a set of proofs confirming that Q-Learning with such delays converges to the optimal policy." @default.
- W2171700688 created "2016-06-24" @default.
- W2171700688 creator A5024133256 @default.
- W2171700688 creator A5063480258 @default.
- W2171700688 date "2007-08-01" @default.
- W2171700688 modified "2023-09-24" @default.
- W2171700688 title "Large-scale tabular-form hardware architecture for Q-Learning with delays" @default.
- W2171700688 cites W1826343992 @default.
- W2171700688 cites W2026076901 @default.
- W2171700688 cites W2054987519 @default.
- W2171700688 cites W2117864026 @default.
- W2171700688 cites W3013672175 @default.
- W2171700688 doi "https://doi.org/10.1109/mwscas.2007.4488701" @default.
- W2171700688 hasPublicationYear "2007" @default.
- W2171700688 type Work @default.
- W2171700688 sameAs 2171700688 @default.
- W2171700688 citedByCount "1" @default.
- W2171700688 countsByYear W21717006882020 @default.
- W2171700688 crossrefType "proceedings-article" @default.
- W2171700688 hasAuthorship W2171700688A5024133256 @default.
- W2171700688 hasAuthorship W2171700688A5063480258 @default.
- W2171700688 hasConcept C108710211 @default.
- W2171700688 hasConcept C121332964 @default.
- W2171700688 hasConcept C123657996 @default.
- W2171700688 hasConcept C126255220 @default.
- W2171700688 hasConcept C14036430 @default.
- W2171700688 hasConcept C142362112 @default.
- W2171700688 hasConcept C14646407 @default.
- W2171700688 hasConcept C149635348 @default.
- W2171700688 hasConcept C153349607 @default.
- W2171700688 hasConcept C154945302 @default.
- W2171700688 hasConcept C166109690 @default.
- W2171700688 hasConcept C169760540 @default.
- W2171700688 hasConcept C177264268 @default.
- W2171700688 hasConcept C188116033 @default.
- W2171700688 hasConcept C199360897 @default.
- W2171700688 hasConcept C2524010 @default.
- W2171700688 hasConcept C26760741 @default.
- W2171700688 hasConcept C2778755073 @default.
- W2171700688 hasConcept C2780513914 @default.
- W2171700688 hasConcept C2780791683 @default.
- W2171700688 hasConcept C33923547 @default.
- W2171700688 hasConcept C41008148 @default.
- W2171700688 hasConcept C62520636 @default.
- W2171700688 hasConcept C78458016 @default.
- W2171700688 hasConcept C81917197 @default.
- W2171700688 hasConcept C86803240 @default.
- W2171700688 hasConcept C97541855 @default.
- W2171700688 hasConceptScore W2171700688C108710211 @default.
- W2171700688 hasConceptScore W2171700688C121332964 @default.
- W2171700688 hasConceptScore W2171700688C123657996 @default.
- W2171700688 hasConceptScore W2171700688C126255220 @default.
- W2171700688 hasConceptScore W2171700688C14036430 @default.
- W2171700688 hasConceptScore W2171700688C142362112 @default.
- W2171700688 hasConceptScore W2171700688C14646407 @default.
- W2171700688 hasConceptScore W2171700688C149635348 @default.
- W2171700688 hasConceptScore W2171700688C153349607 @default.
- W2171700688 hasConceptScore W2171700688C154945302 @default.
- W2171700688 hasConceptScore W2171700688C166109690 @default.
- W2171700688 hasConceptScore W2171700688C169760540 @default.
- W2171700688 hasConceptScore W2171700688C177264268 @default.
- W2171700688 hasConceptScore W2171700688C188116033 @default.
- W2171700688 hasConceptScore W2171700688C199360897 @default.
- W2171700688 hasConceptScore W2171700688C2524010 @default.
- W2171700688 hasConceptScore W2171700688C26760741 @default.
- W2171700688 hasConceptScore W2171700688C2778755073 @default.
- W2171700688 hasConceptScore W2171700688C2780513914 @default.
- W2171700688 hasConceptScore W2171700688C2780791683 @default.
- W2171700688 hasConceptScore W2171700688C33923547 @default.
- W2171700688 hasConceptScore W2171700688C41008148 @default.
- W2171700688 hasConceptScore W2171700688C62520636 @default.
- W2171700688 hasConceptScore W2171700688C78458016 @default.
- W2171700688 hasConceptScore W2171700688C81917197 @default.
- W2171700688 hasConceptScore W2171700688C86803240 @default.
- W2171700688 hasConceptScore W2171700688C97541855 @default.
- W2171700688 hasLocation W21717006881 @default.
- W2171700688 hasOpenAccess W2171700688 @default.
- W2171700688 hasPrimaryLocation W21717006881 @default.
- W2171700688 hasRelatedWork W1587318060 @default.
- W2171700688 hasRelatedWork W2059069309 @default.
- W2171700688 hasRelatedWork W2105523899 @default.
- W2171700688 hasRelatedWork W2120968583 @default.
- W2171700688 hasRelatedWork W2136719210 @default.
- W2171700688 hasRelatedWork W2151416233 @default.
- W2171700688 hasRelatedWork W2170607316 @default.
- W2171700688 hasRelatedWork W2171700688 @default.
- W2171700688 hasRelatedWork W2183243664 @default.
- W2171700688 hasRelatedWork W3145221406 @default.
- W2171700688 isParatext "false" @default.
- W2171700688 isRetracted "false" @default.
- W2171700688 magId "2171700688" @default.
- W2171700688 workType "article" @default.