Matches in SemOpenAlex for { <https://semopenalex.org/work/W3083005225> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3083005225 abstract "This paper offers a new hybrid probably asymptotically correct (PAC) reinforcement learning (RL) algorithm for Markov decision processes (MDPs) that intelligently maintains favorable features of its parents. The designed algorithm, referred to as the Dyna-Delayed Q-learning (DDQ) algorithm, combines model-free and model-based learning approaches while outperforming both in most cases. The paper includes a PAC analysis of the DDQ algorithm and a derivation of its sample complexity. Numerical results that support the claim regarding the new algorithm's sample efficiency compared to its parents are showcased in a small grid-world example." @default.
- W3083005225 created "2020-09-11" @default.
- W3083005225 creator A5042204155 @default.
- W3083005225 creator A5059465693 @default.
- W3083005225 date "2020-09-05" @default.
- W3083005225 modified "2023-09-27" @default.
- W3083005225 title "A Hybrid PAC Reinforcement Learning Algorithm" @default.
- W3083005225 cites W1505937442 @default.
- W3083005225 cites W1511400694 @default.
- W3083005225 cites W1969276875 @default.
- W3083005225 cites W1980035368 @default.
- W3083005225 cites W1988526405 @default.
- W3083005225 cites W2082691056 @default.
- W3083005225 cites W2120678009 @default.
- W3083005225 cites W2123979492 @default.
- W3083005225 cites W2129299900 @default.
- W3083005225 cites W2149166950 @default.
- W3083005225 cites W2737037192 @default.
- W3083005225 cites W2787757704 @default.
- W3083005225 cites W2887305258 @default.
- W3083005225 cites W2911931139 @default.
- W3083005225 cites W2951948137 @default.
- W3083005225 cites W2962872206 @default.
- W3083005225 cites W567721252 @default.
- W3083005225 hasPublicationYear "2020" @default.
- W3083005225 type Work @default.
- W3083005225 sameAs 3083005225 @default.
- W3083005225 citedByCount "0" @default.
- W3083005225 crossrefType "posted-content" @default.
- W3083005225 hasAuthorship W3083005225A5042204155 @default.
- W3083005225 hasAuthorship W3083005225A5059465693 @default.
- W3083005225 hasConcept C105795698 @default.
- W3083005225 hasConcept C106189395 @default.
- W3083005225 hasConcept C11413529 @default.
- W3083005225 hasConcept C119857082 @default.
- W3083005225 hasConcept C154945302 @default.
- W3083005225 hasConcept C159886148 @default.
- W3083005225 hasConcept C176783269 @default.
- W3083005225 hasConcept C185592680 @default.
- W3083005225 hasConcept C187691185 @default.
- W3083005225 hasConcept C188116033 @default.
- W3083005225 hasConcept C198531522 @default.
- W3083005225 hasConcept C2524010 @default.
- W3083005225 hasConcept C2778445095 @default.
- W3083005225 hasConcept C33923547 @default.
- W3083005225 hasConcept C41008148 @default.
- W3083005225 hasConcept C43617362 @default.
- W3083005225 hasConcept C44616089 @default.
- W3083005225 hasConcept C49937458 @default.
- W3083005225 hasConcept C62469222 @default.
- W3083005225 hasConcept C97541855 @default.
- W3083005225 hasConcept C98763669 @default.
- W3083005225 hasConceptScore W3083005225C105795698 @default.
- W3083005225 hasConceptScore W3083005225C106189395 @default.
- W3083005225 hasConceptScore W3083005225C11413529 @default.
- W3083005225 hasConceptScore W3083005225C119857082 @default.
- W3083005225 hasConceptScore W3083005225C154945302 @default.
- W3083005225 hasConceptScore W3083005225C159886148 @default.
- W3083005225 hasConceptScore W3083005225C176783269 @default.
- W3083005225 hasConceptScore W3083005225C185592680 @default.
- W3083005225 hasConceptScore W3083005225C187691185 @default.
- W3083005225 hasConceptScore W3083005225C188116033 @default.
- W3083005225 hasConceptScore W3083005225C198531522 @default.
- W3083005225 hasConceptScore W3083005225C2524010 @default.
- W3083005225 hasConceptScore W3083005225C2778445095 @default.
- W3083005225 hasConceptScore W3083005225C33923547 @default.
- W3083005225 hasConceptScore W3083005225C41008148 @default.
- W3083005225 hasConceptScore W3083005225C43617362 @default.
- W3083005225 hasConceptScore W3083005225C44616089 @default.
- W3083005225 hasConceptScore W3083005225C49937458 @default.
- W3083005225 hasConceptScore W3083005225C62469222 @default.
- W3083005225 hasConceptScore W3083005225C97541855 @default.
- W3083005225 hasConceptScore W3083005225C98763669 @default.
- W3083005225 hasLocation W30830052251 @default.
- W3083005225 hasOpenAccess W3083005225 @default.
- W3083005225 hasPrimaryLocation W30830052251 @default.
- W3083005225 hasRelatedWork W1492936035 @default.
- W3083005225 hasRelatedWork W1537180453 @default.
- W3083005225 hasRelatedWork W2020753891 @default.
- W3083005225 hasRelatedWork W2112899086 @default.
- W3083005225 hasRelatedWork W2114876262 @default.
- W3083005225 hasRelatedWork W2127270832 @default.
- W3083005225 hasRelatedWork W2129670787 @default.
- W3083005225 hasRelatedWork W2388085239 @default.
- W3083005225 hasRelatedWork W2557003457 @default.
- W3083005225 hasRelatedWork W2808421695 @default.
- W3083005225 hasRelatedWork W2917322258 @default.
- W3083005225 hasRelatedWork W2944987817 @default.
- W3083005225 hasRelatedWork W3001618744 @default.
- W3083005225 hasRelatedWork W3037308930 @default.
- W3083005225 hasRelatedWork W3038032959 @default.
- W3083005225 hasRelatedWork W3083441818 @default.
- W3083005225 hasRelatedWork W3126245445 @default.
- W3083005225 hasRelatedWork W3178256563 @default.
- W3083005225 hasRelatedWork W62417866 @default.
- W3083005225 hasRelatedWork W2435049346 @default.
- W3083005225 isParatext "false" @default.
- W3083005225 isRetracted "false" @default.
- W3083005225 magId "3083005225" @default.
- W3083005225 workType "article" @default.