Matches in SemOpenAlex for { <https://semopenalex.org/work/W2943107978> ?p ?o ?g. }
- W2943107978 endingPage "932" @default.
- W2943107978 startingPage "901" @default.
- W2943107978 abstract "Heuristically accelerated reinforcement learning (HARL) is a new family of algorithms that combines the advantages of reinforcement learning (RL) with the advantages of heuristic algorithms. To achieve this, the action selection strategy of the standard RL algorithm is modified to take into account a heuristic running in parallel with the RL process. This paper presents two approximated HARL algorithms that make use of pheromone trails to improve the behaviour of linearly approximated SARSA( $$lambda $$ ) by dynamically learning a heuristic function through the pheromone trails. The proposed dynamic algorithms are evaluated in comparison to linearly approximated SARSA( $$lambda $$ ), and heuristically accelerated SARSA( $$lambda $$ ) using a static heuristic in three benchmark scenarios: the mountain car, the mountain car 3D and the maze scenarios." @default.
- W2943107978 created "2019-05-09" @default.
- W2943107978 creator A5060319953 @default.
- W2943107978 date "2019-05-03" @default.
- W2943107978 modified "2023-09-28" @default.
- W2943107978 title "Dynamic heuristic acceleration of linearly approximated SARSA($$lambda $$): using ant colony optimization to learn heuristics dynamically" @default.
- W2943107978 cites W1519972694 @default.
- W2943107978 cites W1801849579 @default.
- W2943107978 cites W1965202052 @default.
- W2943107978 cites W1968150523 @default.
- W2943107978 cites W1975009952 @default.
- W2943107978 cites W1982262386 @default.
- W2943107978 cites W1982955044 @default.
- W2943107978 cites W1997547316 @default.
- W2943107978 cites W2005183808 @default.
- W2943107978 cites W2008809493 @default.
- W2943107978 cites W2021004298 @default.
- W2943107978 cites W2053871929 @default.
- W2943107978 cites W206679605 @default.
- W2943107978 cites W2075022759 @default.
- W2943107978 cites W2098477891 @default.
- W2943107978 cites W2107941094 @default.
- W2943107978 cites W2118573797 @default.
- W2943107978 cites W2130411910 @default.
- W2943107978 cites W2134689794 @default.
- W2943107978 cites W2134698488 @default.
- W2943107978 cites W2137564278 @default.
- W2943107978 cites W2151340488 @default.
- W2943107978 cites W2151661095 @default.
- W2943107978 cites W2154929945 @default.
- W2943107978 cites W2168650344 @default.
- W2943107978 cites W2170375089 @default.
- W2943107978 cites W2257979135 @default.
- W2943107978 cites W2395579298 @default.
- W2943107978 cites W2396820603 @default.
- W2943107978 cites W2543580944 @default.
- W2943107978 cites W2614992370 @default.
- W2943107978 cites W2919115771 @default.
- W2943107978 cites W4214717370 @default.
- W2943107978 cites W605348272 @default.
- W2943107978 cites W1998005630 @default.
- W2943107978 doi "https://doi.org/10.1007/s10732-019-09408-x" @default.
- W2943107978 hasPublicationYear "2019" @default.
- W2943107978 type Work @default.
- W2943107978 sameAs 2943107978 @default.
- W2943107978 citedByCount "2" @default.
- W2943107978 countsByYear W29431079782019 @default.
- W2943107978 countsByYear W29431079782020 @default.
- W2943107978 crossrefType "journal-article" @default.
- W2943107978 hasAuthorship W2943107978A5060319953 @default.
- W2943107978 hasBestOaLocation W29431079781 @default.
- W2943107978 hasConcept C11413529 @default.
- W2943107978 hasConcept C117896860 @default.
- W2943107978 hasConcept C121332964 @default.
- W2943107978 hasConcept C126255220 @default.
- W2943107978 hasConcept C127705205 @default.
- W2943107978 hasConcept C13280743 @default.
- W2943107978 hasConcept C154945302 @default.
- W2943107978 hasConcept C173801870 @default.
- W2943107978 hasConcept C175859090 @default.
- W2943107978 hasConcept C185798385 @default.
- W2943107978 hasConcept C205649164 @default.
- W2943107978 hasConcept C33923547 @default.
- W2943107978 hasConcept C40128228 @default.
- W2943107978 hasConcept C41008148 @default.
- W2943107978 hasConcept C74650414 @default.
- W2943107978 hasConcept C97541855 @default.
- W2943107978 hasConceptScore W2943107978C11413529 @default.
- W2943107978 hasConceptScore W2943107978C117896860 @default.
- W2943107978 hasConceptScore W2943107978C121332964 @default.
- W2943107978 hasConceptScore W2943107978C126255220 @default.
- W2943107978 hasConceptScore W2943107978C127705205 @default.
- W2943107978 hasConceptScore W2943107978C13280743 @default.
- W2943107978 hasConceptScore W2943107978C154945302 @default.
- W2943107978 hasConceptScore W2943107978C173801870 @default.
- W2943107978 hasConceptScore W2943107978C175859090 @default.
- W2943107978 hasConceptScore W2943107978C185798385 @default.
- W2943107978 hasConceptScore W2943107978C205649164 @default.
- W2943107978 hasConceptScore W2943107978C33923547 @default.
- W2943107978 hasConceptScore W2943107978C40128228 @default.
- W2943107978 hasConceptScore W2943107978C41008148 @default.
- W2943107978 hasConceptScore W2943107978C74650414 @default.
- W2943107978 hasConceptScore W2943107978C97541855 @default.
- W2943107978 hasIssue "6" @default.
- W2943107978 hasLocation W29431079781 @default.
- W2943107978 hasOpenAccess W2943107978 @default.
- W2943107978 hasPrimaryLocation W29431079781 @default.
- W2943107978 hasRelatedWork W1565836903 @default.
- W2943107978 hasRelatedWork W1985001989 @default.
- W2943107978 hasRelatedWork W2020351850 @default.
- W2943107978 hasRelatedWork W2089906373 @default.
- W2943107978 hasRelatedWork W2105159953 @default.
- W2943107978 hasRelatedWork W2324432194 @default.
- W2943107978 hasRelatedWork W2374826131 @default.
- W2943107978 hasRelatedWork W2581156000 @default.
- W2943107978 hasRelatedWork W2892176789 @default.
- W2943107978 hasRelatedWork W3001781807 @default.
- W2943107978 hasRelatedWork W3017062736 @default.