Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387635236> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4387635236 abstract "Temporal difference learning (TD) is a foundational concept in reinforcement learning (RL), aimed at efficiently assessing a policy's value function. TD($lambda$), a potent variant, incorporates a memory trace to distribute the prediction error into the historical context. However, this approach often neglects the significance of historical states and the relative importance of propagating the TD error, influenced by challenges such as visitation imbalance or outcome noise. To address this, we propose a novel TD algorithm named discerning TD learning (DTD), which allows flexible emphasis functions$-$predetermined or adapted during training$-$to allocate efforts effectively across states. We establish the convergence properties of our method within a specific class of emphasis functions and showcase its promising potential for adaptation to deep RL contexts. Empirical results underscore that employing a judicious emphasis function not only improves value estimation but also expedites learning across diverse scenarios." @default.
- W4387635236 created "2023-10-14" @default.
- W4387635236 creator A5042256955 @default.
- W4387635236 date "2023-10-12" @default.
- W4387635236 modified "2023-10-15" @default.
- W4387635236 title "Discerning Temporal Difference Learning" @default.
- W4387635236 doi "https://doi.org/10.48550/arxiv.2310.08091" @default.
- W4387635236 hasPublicationYear "2023" @default.
- W4387635236 type Work @default.
- W4387635236 citedByCount "0" @default.
- W4387635236 crossrefType "posted-content" @default.
- W4387635236 hasAuthorship W4387635236A5042256955 @default.
- W4387635236 hasBestOaLocation W43876352361 @default.
- W4387635236 hasConcept C115961682 @default.
- W4387635236 hasConcept C119857082 @default.
- W4387635236 hasConcept C126255220 @default.
- W4387635236 hasConcept C138885662 @default.
- W4387635236 hasConcept C139807058 @default.
- W4387635236 hasConcept C14036430 @default.
- W4387635236 hasConcept C14646407 @default.
- W4387635236 hasConcept C151730666 @default.
- W4387635236 hasConcept C154945302 @default.
- W4387635236 hasConcept C15744967 @default.
- W4387635236 hasConcept C162324750 @default.
- W4387635236 hasConcept C169760540 @default.
- W4387635236 hasConcept C177454536 @default.
- W4387635236 hasConcept C196340769 @default.
- W4387635236 hasConcept C2776291640 @default.
- W4387635236 hasConcept C2777212361 @default.
- W4387635236 hasConcept C2777303404 @default.
- W4387635236 hasConcept C2779343474 @default.
- W4387635236 hasConcept C33923547 @default.
- W4387635236 hasConcept C41008148 @default.
- W4387635236 hasConcept C41895202 @default.
- W4387635236 hasConcept C50522688 @default.
- W4387635236 hasConcept C75291252 @default.
- W4387635236 hasConcept C76155785 @default.
- W4387635236 hasConcept C78458016 @default.
- W4387635236 hasConcept C86803240 @default.
- W4387635236 hasConcept C97541855 @default.
- W4387635236 hasConcept C99498987 @default.
- W4387635236 hasConceptScore W4387635236C115961682 @default.
- W4387635236 hasConceptScore W4387635236C119857082 @default.
- W4387635236 hasConceptScore W4387635236C126255220 @default.
- W4387635236 hasConceptScore W4387635236C138885662 @default.
- W4387635236 hasConceptScore W4387635236C139807058 @default.
- W4387635236 hasConceptScore W4387635236C14036430 @default.
- W4387635236 hasConceptScore W4387635236C14646407 @default.
- W4387635236 hasConceptScore W4387635236C151730666 @default.
- W4387635236 hasConceptScore W4387635236C154945302 @default.
- W4387635236 hasConceptScore W4387635236C15744967 @default.
- W4387635236 hasConceptScore W4387635236C162324750 @default.
- W4387635236 hasConceptScore W4387635236C169760540 @default.
- W4387635236 hasConceptScore W4387635236C177454536 @default.
- W4387635236 hasConceptScore W4387635236C196340769 @default.
- W4387635236 hasConceptScore W4387635236C2776291640 @default.
- W4387635236 hasConceptScore W4387635236C2777212361 @default.
- W4387635236 hasConceptScore W4387635236C2777303404 @default.
- W4387635236 hasConceptScore W4387635236C2779343474 @default.
- W4387635236 hasConceptScore W4387635236C33923547 @default.
- W4387635236 hasConceptScore W4387635236C41008148 @default.
- W4387635236 hasConceptScore W4387635236C41895202 @default.
- W4387635236 hasConceptScore W4387635236C50522688 @default.
- W4387635236 hasConceptScore W4387635236C75291252 @default.
- W4387635236 hasConceptScore W4387635236C76155785 @default.
- W4387635236 hasConceptScore W4387635236C78458016 @default.
- W4387635236 hasConceptScore W4387635236C86803240 @default.
- W4387635236 hasConceptScore W4387635236C97541855 @default.
- W4387635236 hasConceptScore W4387635236C99498987 @default.
- W4387635236 hasLocation W43876352361 @default.
- W4387635236 hasOpenAccess W4387635236 @default.
- W4387635236 hasPrimaryLocation W43876352361 @default.
- W4387635236 hasRelatedWork W2025663273 @default.
- W4387635236 hasRelatedWork W2145363145 @default.
- W4387635236 hasRelatedWork W2154399718 @default.
- W4387635236 hasRelatedWork W2341346307 @default.
- W4387635236 hasRelatedWork W2386410636 @default.
- W4387635236 hasRelatedWork W3038962357 @default.
- W4387635236 hasRelatedWork W3099153698 @default.
- W4387635236 hasRelatedWork W4313679781 @default.
- W4387635236 hasRelatedWork W4321463377 @default.
- W4387635236 hasRelatedWork W4387019592 @default.
- W4387635236 isParatext "false" @default.
- W4387635236 isRetracted "false" @default.
- W4387635236 workType "article" @default.