Matches in SemOpenAlex for { <https://semopenalex.org/work/W72400652> ?p ?o ?g. }
- W72400652 endingPage "1447" @default.
- W72400652 startingPage "1445" @default.
- W72400652 abstract "We present a new algorithm, GM-Sarsa(O), for finding approximate solutions to multiple-goal reinforcement learning problems that are modeled as composite Markov decision processes. According to our formulation different sub-goals are modeled as MDPs that are coupled by the requirement that they share actions. Existing reinforcement learning algorithms address similar problem formulations by first finding optimal policies for the component MDPs, and then merging these into a policy for the composite task. The problem with such methods is that policies that are optimized separately may or may not perform well when they are merged into a composite solution. Instead of searching for optimal policies for the component MDPs in isolation, our approach finds good policies in the context of the composite task." @default.
- W72400652 created "2016-06-24" @default.
- W72400652 creator A5002822166 @default.
- W72400652 creator A5089617051 @default.
- W72400652 date "2003-08-09" @default.
- W72400652 modified "2023-09-23" @default.
- W72400652 title "Multiple-goal reinforcement learning with modular Sarsa(O)" @default.
- W72400652 cites W1480676279 @default.
- W72400652 cites W2113913482 @default.
- W72400652 cites W2114958204 @default.
- W72400652 cites W2121517924 @default.
- W72400652 cites W2124175081 @default.
- W72400652 cites W2126566174 @default.
- W72400652 cites W2129307307 @default.
- W72400652 cites W2137466452 @default.
- W72400652 cites W2147492008 @default.
- W72400652 cites W2150339816 @default.
- W72400652 cites W24785488 @default.
- W72400652 cites W3139377883 @default.
- W72400652 cites W6242441 @default.
- W72400652 hasPublicationYear "2003" @default.
- W72400652 type Work @default.
- W72400652 sameAs 72400652 @default.
- W72400652 citedByCount "46" @default.
- W72400652 countsByYear W724006522013 @default.
- W72400652 countsByYear W724006522015 @default.
- W72400652 countsByYear W724006522017 @default.
- W72400652 countsByYear W724006522018 @default.
- W72400652 countsByYear W724006522019 @default.
- W72400652 countsByYear W724006522020 @default.
- W72400652 countsByYear W724006522021 @default.
- W72400652 crossrefType "proceedings-article" @default.
- W72400652 hasAuthorship W72400652A5002822166 @default.
- W72400652 hasAuthorship W72400652A5089617051 @default.
- W72400652 hasConcept C101468663 @default.
- W72400652 hasConcept C105795698 @default.
- W72400652 hasConcept C106189395 @default.
- W72400652 hasConcept C111919701 @default.
- W72400652 hasConcept C119857082 @default.
- W72400652 hasConcept C121332964 @default.
- W72400652 hasConcept C126255220 @default.
- W72400652 hasConcept C127413603 @default.
- W72400652 hasConcept C151730666 @default.
- W72400652 hasConcept C154945302 @default.
- W72400652 hasConcept C159886148 @default.
- W72400652 hasConcept C168167062 @default.
- W72400652 hasConcept C201995342 @default.
- W72400652 hasConcept C2779343474 @default.
- W72400652 hasConcept C2780451532 @default.
- W72400652 hasConcept C33923547 @default.
- W72400652 hasConcept C41008148 @default.
- W72400652 hasConcept C66938386 @default.
- W72400652 hasConcept C67203356 @default.
- W72400652 hasConcept C86803240 @default.
- W72400652 hasConcept C97355855 @default.
- W72400652 hasConcept C97541855 @default.
- W72400652 hasConceptScore W72400652C101468663 @default.
- W72400652 hasConceptScore W72400652C105795698 @default.
- W72400652 hasConceptScore W72400652C106189395 @default.
- W72400652 hasConceptScore W72400652C111919701 @default.
- W72400652 hasConceptScore W72400652C119857082 @default.
- W72400652 hasConceptScore W72400652C121332964 @default.
- W72400652 hasConceptScore W72400652C126255220 @default.
- W72400652 hasConceptScore W72400652C127413603 @default.
- W72400652 hasConceptScore W72400652C151730666 @default.
- W72400652 hasConceptScore W72400652C154945302 @default.
- W72400652 hasConceptScore W72400652C159886148 @default.
- W72400652 hasConceptScore W72400652C168167062 @default.
- W72400652 hasConceptScore W72400652C201995342 @default.
- W72400652 hasConceptScore W72400652C2779343474 @default.
- W72400652 hasConceptScore W72400652C2780451532 @default.
- W72400652 hasConceptScore W72400652C33923547 @default.
- W72400652 hasConceptScore W72400652C41008148 @default.
- W72400652 hasConceptScore W72400652C66938386 @default.
- W72400652 hasConceptScore W72400652C67203356 @default.
- W72400652 hasConceptScore W72400652C86803240 @default.
- W72400652 hasConceptScore W72400652C97355855 @default.
- W72400652 hasConceptScore W72400652C97541855 @default.
- W72400652 hasLocation W724006521 @default.
- W72400652 hasOpenAccess W72400652 @default.
- W72400652 hasPrimaryLocation W724006521 @default.
- W72400652 hasRelatedWork W1480676279 @default.
- W72400652 hasRelatedWork W1488730473 @default.
- W72400652 hasRelatedWork W1515851193 @default.
- W72400652 hasRelatedWork W1592847719 @default.
- W72400652 hasRelatedWork W1998560962 @default.
- W72400652 hasRelatedWork W1999874108 @default.
- W72400652 hasRelatedWork W2061562262 @default.
- W72400652 hasRelatedWork W2097856935 @default.
- W72400652 hasRelatedWork W2103582821 @default.
- W72400652 hasRelatedWork W2107726111 @default.
- W72400652 hasRelatedWork W2109910161 @default.
- W72400652 hasRelatedWork W2121863487 @default.
- W72400652 hasRelatedWork W2136202932 @default.
- W72400652 hasRelatedWork W2145339207 @default.
- W72400652 hasRelatedWork W2158548602 @default.
- W72400652 hasRelatedWork W24785488 @default.
- W72400652 hasRelatedWork W2624731731 @default.