Matches in SemOpenAlex for { <https://semopenalex.org/work/W36691172> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W36691172 endingPage "499" @default.
- W36691172 startingPage "494" @default.
- W36691172 abstract "We examine the problem of Transfer in Reinforcement Learning and present a method to utilize knowledge acquired in one Markov Decision Process (MDP) to bootstrap learning in a more complex but related MDP. We build on work in model minimization in Reinforcement Learning to define relationships between state-action pairs of the two MDPs. Our main contribution in this work is to provide a way to compactly represent such mappings using relationships between state variables in the two domains. We use these functions to transfer a learned policy in the first domain into an option in the new domain, and apply intra-option learning methods to bootstrap learning in the new domain. We first evaluate our approach in the well known Blocksworld domain. We then demonstrate that our approach to transfer is viable in a complex domain with a continuous state space by evaluating it in the Robosoccer Keepaway domain." @default.
- W36691172 created "2016-06-24" @default.
- W36691172 creator A5065366930 @default.
- W36691172 creator A5066325003 @default.
- W36691172 date "2006-07-16" @default.
- W36691172 modified "2023-09-24" @default.
- W36691172 title "Using Homomorphisms to transfer options across continuous reinforcement learning domains" @default.
- W36691172 cites W1494114146 @default.
- W36691172 cites W1515851193 @default.
- W36691172 cites W1534331386 @default.
- W36691172 cites W1564393562 @default.
- W36691172 cites W1688218840 @default.
- W36691172 cites W2104641222 @default.
- W36691172 cites W2109910161 @default.
- W36691172 cites W2121863487 @default.
- W36691172 cites W2126565096 @default.
- W36691172 hasPublicationYear "2006" @default.
- W36691172 type Work @default.
- W36691172 sameAs 36691172 @default.
- W36691172 citedByCount "37" @default.
- W36691172 countsByYear W366911722012 @default.
- W36691172 countsByYear W366911722013 @default.
- W36691172 countsByYear W366911722014 @default.
- W36691172 countsByYear W366911722015 @default.
- W36691172 countsByYear W366911722016 @default.
- W36691172 countsByYear W366911722017 @default.
- W36691172 countsByYear W366911722018 @default.
- W36691172 countsByYear W366911722019 @default.
- W36691172 countsByYear W366911722020 @default.
- W36691172 crossrefType "proceedings-article" @default.
- W36691172 hasAuthorship W36691172A5065366930 @default.
- W36691172 hasAuthorship W36691172A5066325003 @default.
- W36691172 hasConcept C105795698 @default.
- W36691172 hasConcept C106189395 @default.
- W36691172 hasConcept C118615104 @default.
- W36691172 hasConcept C119857082 @default.
- W36691172 hasConcept C134306372 @default.
- W36691172 hasConcept C150899416 @default.
- W36691172 hasConcept C154945302 @default.
- W36691172 hasConcept C159886148 @default.
- W36691172 hasConcept C33923547 @default.
- W36691172 hasConcept C36503486 @default.
- W36691172 hasConcept C4042151 @default.
- W36691172 hasConcept C41008148 @default.
- W36691172 hasConcept C72434380 @default.
- W36691172 hasConcept C80444323 @default.
- W36691172 hasConcept C97541855 @default.
- W36691172 hasConcept C98763669 @default.
- W36691172 hasConceptScore W36691172C105795698 @default.
- W36691172 hasConceptScore W36691172C106189395 @default.
- W36691172 hasConceptScore W36691172C118615104 @default.
- W36691172 hasConceptScore W36691172C119857082 @default.
- W36691172 hasConceptScore W36691172C134306372 @default.
- W36691172 hasConceptScore W36691172C150899416 @default.
- W36691172 hasConceptScore W36691172C154945302 @default.
- W36691172 hasConceptScore W36691172C159886148 @default.
- W36691172 hasConceptScore W36691172C33923547 @default.
- W36691172 hasConceptScore W36691172C36503486 @default.
- W36691172 hasConceptScore W36691172C4042151 @default.
- W36691172 hasConceptScore W36691172C41008148 @default.
- W36691172 hasConceptScore W36691172C72434380 @default.
- W36691172 hasConceptScore W36691172C80444323 @default.
- W36691172 hasConceptScore W36691172C97541855 @default.
- W36691172 hasConceptScore W36691172C98763669 @default.
- W36691172 hasLocation W366911721 @default.
- W36691172 hasOpenAccess W36691172 @default.
- W36691172 hasPrimaryLocation W366911721 @default.
- W36691172 hasRelatedWork W1506146479 @default.
- W36691172 hasRelatedWork W1515851193 @default.
- W36691172 hasRelatedWork W2004030284 @default.
- W36691172 hasRelatedWork W2031727428 @default.
- W36691172 hasRelatedWork W2079247031 @default.
- W36691172 hasRelatedWork W2097381042 @default.
- W36691172 hasRelatedWork W2098723043 @default.
- W36691172 hasRelatedWork W2104641222 @default.
- W36691172 hasRelatedWork W2109910161 @default.
- W36691172 hasRelatedWork W2110292307 @default.
- W36691172 hasRelatedWork W2121517924 @default.
- W36691172 hasRelatedWork W2121863487 @default.
- W36691172 hasRelatedWork W2128905965 @default.
- W36691172 hasRelatedWork W2133040789 @default.
- W36691172 hasRelatedWork W2153353285 @default.
- W36691172 hasRelatedWork W2158150115 @default.
- W36691172 hasRelatedWork W2164114810 @default.
- W36691172 hasRelatedWork W2169743339 @default.
- W36691172 hasRelatedWork W3011120880 @default.
- W36691172 hasRelatedWork W3139377883 @default.
- W36691172 isParatext "false" @default.
- W36691172 isRetracted "false" @default.
- W36691172 magId "36691172" @default.
- W36691172 workType "article" @default.