Matches in SemOpenAlex for { <https://semopenalex.org/work/W2787236409> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2787236409 abstract "Exploration is a fundamental aspect of Reinforcement Learning, typically implemented using stochastic action-selection. Exploration, however, can be more efficient if directed toward gaining new world knowledge. Visit-counters have been proven useful both in practice and in theory for directed exploration. However, a major limitation of counters is their locality. While there are a few model-based solutions to this shortcoming, a model-free approach is still missing. We propose $E$-values, a generalization of counters that can be used to evaluate the propagating exploratory value over state-action trajectories. We compare our approach to commonly used RL techniques, and show that using $E$-values improves learning and performance over traditional counters. We also show how our method can be implemented with function approximation to efficiently learn continuous MDPs. We demonstrate this by showing that our approach surpasses state of the art performance in the Freeway Atari 2600 game." @default.
- W2787236409 created "2018-02-23" @default.
- W2787236409 creator A5019527475 @default.
- W2787236409 creator A5040286212 @default.
- W2787236409 creator A5074945649 @default.
- W2787236409 date "2018-04-11" @default.
- W2787236409 modified "2023-10-15" @default.
- W2787236409 title "DORA The Explorer: Directed Outreaching Reinforcement Action-Selection" @default.
- W2787236409 hasPublicationYear "2018" @default.
- W2787236409 type Work @default.
- W2787236409 sameAs 2787236409 @default.
- W2787236409 citedByCount "16" @default.
- W2787236409 countsByYear W27872364092017 @default.
- W2787236409 countsByYear W27872364092018 @default.
- W2787236409 countsByYear W27872364092019 @default.
- W2787236409 countsByYear W27872364092020 @default.
- W2787236409 countsByYear W27872364092021 @default.
- W2787236409 crossrefType "posted-content" @default.
- W2787236409 hasAuthorship W2787236409A5019527475 @default.
- W2787236409 hasAuthorship W2787236409A5040286212 @default.
- W2787236409 hasAuthorship W2787236409A5074945649 @default.
- W2787236409 hasConcept C11413529 @default.
- W2787236409 hasConcept C119857082 @default.
- W2787236409 hasConcept C121332964 @default.
- W2787236409 hasConcept C126255220 @default.
- W2787236409 hasConcept C134306372 @default.
- W2787236409 hasConcept C138885662 @default.
- W2787236409 hasConcept C14036430 @default.
- W2787236409 hasConcept C14646407 @default.
- W2787236409 hasConcept C154945302 @default.
- W2787236409 hasConcept C166109690 @default.
- W2787236409 hasConcept C169760540 @default.
- W2787236409 hasConcept C177148314 @default.
- W2787236409 hasConcept C26760741 @default.
- W2787236409 hasConcept C2779808786 @default.
- W2787236409 hasConcept C2780791683 @default.
- W2787236409 hasConcept C33923547 @default.
- W2787236409 hasConcept C41008148 @default.
- W2787236409 hasConcept C41895202 @default.
- W2787236409 hasConcept C48103436 @default.
- W2787236409 hasConcept C62520636 @default.
- W2787236409 hasConcept C78458016 @default.
- W2787236409 hasConcept C81917197 @default.
- W2787236409 hasConcept C86803240 @default.
- W2787236409 hasConcept C97541855 @default.
- W2787236409 hasConceptScore W2787236409C11413529 @default.
- W2787236409 hasConceptScore W2787236409C119857082 @default.
- W2787236409 hasConceptScore W2787236409C121332964 @default.
- W2787236409 hasConceptScore W2787236409C126255220 @default.
- W2787236409 hasConceptScore W2787236409C134306372 @default.
- W2787236409 hasConceptScore W2787236409C138885662 @default.
- W2787236409 hasConceptScore W2787236409C14036430 @default.
- W2787236409 hasConceptScore W2787236409C14646407 @default.
- W2787236409 hasConceptScore W2787236409C154945302 @default.
- W2787236409 hasConceptScore W2787236409C166109690 @default.
- W2787236409 hasConceptScore W2787236409C169760540 @default.
- W2787236409 hasConceptScore W2787236409C177148314 @default.
- W2787236409 hasConceptScore W2787236409C26760741 @default.
- W2787236409 hasConceptScore W2787236409C2779808786 @default.
- W2787236409 hasConceptScore W2787236409C2780791683 @default.
- W2787236409 hasConceptScore W2787236409C33923547 @default.
- W2787236409 hasConceptScore W2787236409C41008148 @default.
- W2787236409 hasConceptScore W2787236409C41895202 @default.
- W2787236409 hasConceptScore W2787236409C48103436 @default.
- W2787236409 hasConceptScore W2787236409C62520636 @default.
- W2787236409 hasConceptScore W2787236409C78458016 @default.
- W2787236409 hasConceptScore W2787236409C81917197 @default.
- W2787236409 hasConceptScore W2787236409C86803240 @default.
- W2787236409 hasConceptScore W2787236409C97541855 @default.
- W2787236409 hasLocation W27872364091 @default.
- W2787236409 hasOpenAccess W2787236409 @default.
- W2787236409 hasPrimaryLocation W27872364091 @default.
- W2787236409 hasRelatedWork W1505937442 @default.
- W2787236409 hasRelatedWork W1988526405 @default.
- W2787236409 hasRelatedWork W2121863487 @default.
- W2787236409 hasRelatedWork W2128786740 @default.
- W2787236409 hasRelatedWork W2145339207 @default.
- W2787236409 hasRelatedWork W2160589914 @default.
- W2787236409 hasRelatedWork W2173248099 @default.
- W2787236409 hasRelatedWork W2489939061 @default.
- W2787236409 hasRelatedWork W2561776174 @default.
- W2787236409 hasRelatedWork W2736601468 @default.
- W2787236409 hasRelatedWork W2751973545 @default.
- W2787236409 hasRelatedWork W2899205164 @default.
- W2787236409 hasRelatedWork W2949608212 @default.
- W2787236409 hasRelatedWork W2963276097 @default.
- W2787236409 hasRelatedWork W2963938771 @default.
- W2787236409 hasRelatedWork W2964043796 @default.
- W2787236409 hasRelatedWork W2978242174 @default.
- W2787236409 hasRelatedWork W2982365794 @default.
- W2787236409 hasRelatedWork W2997289589 @default.
- W2787236409 hasRelatedWork W779494576 @default.
- W2787236409 isParatext "false" @default.
- W2787236409 isRetracted "false" @default.
- W2787236409 magId "2787236409" @default.
- W2787236409 workType "article" @default.