Matches in SemOpenAlex for { <https://semopenalex.org/work/W1782523431> ?p ?o ?g. }
- W1782523431 endingPage "53" @default.
- W1782523431 startingPage "42" @default.
- W1782523431 abstract "We consider the active learning problem of inferring the transition model of a Markov Decision Process by acting and observing transitions. This is particularly useful when no reward function is a priori defined. Our proposal is to cast the active learning task as a utility maximization problem using Bayesian reinforcement learning with belief-dependent rewards. After presenting three possible performance criteria, we derive from them the belief-dependent rewards to be used in the decision-making process. As computing the optimal Bayesian value function is intractable for large horizons, we use a simple algorithm to approximately solve this optimization problem. Despite the sub-optimality of this technique, we show experimentally that our proposal is efficient in a number of domains." @default.
- W1782523431 created "2016-06-24" @default.
- W1782523431 creator A5022343068 @default.
- W1782523431 creator A5037765124 @default.
- W1782523431 creator A5051052976 @default.
- W1782523431 creator A5073558695 @default.
- W1782523431 date "2012-01-01" @default.
- W1782523431 modified "2023-09-25" @default.
- W1782523431 title "Active Learning of MDP Models" @default.
- W1782523431 cites W1980516134 @default.
- W1782523431 cites W2027335239 @default.
- W1782523431 cites W2106008679 @default.
- W1782523431 cites W2116459397 @default.
- W1782523431 cites W2124352385 @default.
- W1782523431 cites W2140332127 @default.
- W1782523431 cites W2147692729 @default.
- W1782523431 cites W2334782222 @default.
- W1782523431 cites W4214717370 @default.
- W1782523431 doi "https://doi.org/10.1007/978-3-642-29946-9_8" @default.
- W1782523431 hasPublicationYear "2012" @default.
- W1782523431 type Work @default.
- W1782523431 sameAs 1782523431 @default.
- W1782523431 citedByCount "6" @default.
- W1782523431 countsByYear W17825234312013 @default.
- W1782523431 countsByYear W17825234312017 @default.
- W1782523431 countsByYear W17825234312019 @default.
- W1782523431 countsByYear W17825234312020 @default.
- W1782523431 countsByYear W17825234312022 @default.
- W1782523431 crossrefType "book-chapter" @default.
- W1782523431 hasAuthorship W1782523431A5022343068 @default.
- W1782523431 hasAuthorship W1782523431A5037765124 @default.
- W1782523431 hasAuthorship W1782523431A5051052976 @default.
- W1782523431 hasAuthorship W1782523431A5073558695 @default.
- W1782523431 hasBestOaLocation W17825234312 @default.
- W1782523431 hasConcept C105795698 @default.
- W1782523431 hasConcept C106189395 @default.
- W1782523431 hasConcept C107673813 @default.
- W1782523431 hasConcept C111472728 @default.
- W1782523431 hasConcept C119857082 @default.
- W1782523431 hasConcept C126255220 @default.
- W1782523431 hasConcept C138885662 @default.
- W1782523431 hasConcept C14036430 @default.
- W1782523431 hasConcept C14646407 @default.
- W1782523431 hasConcept C154945302 @default.
- W1782523431 hasConcept C159886148 @default.
- W1782523431 hasConcept C162324750 @default.
- W1782523431 hasConcept C163836022 @default.
- W1782523431 hasConcept C17098449 @default.
- W1782523431 hasConcept C187736073 @default.
- W1782523431 hasConcept C2776330181 @default.
- W1782523431 hasConcept C2778049539 @default.
- W1782523431 hasConcept C2780451532 @default.
- W1782523431 hasConcept C33923547 @default.
- W1782523431 hasConcept C41008148 @default.
- W1782523431 hasConcept C75553542 @default.
- W1782523431 hasConcept C78458016 @default.
- W1782523431 hasConcept C86803240 @default.
- W1782523431 hasConcept C97541855 @default.
- W1782523431 hasConcept C98763669 @default.
- W1782523431 hasConceptScore W1782523431C105795698 @default.
- W1782523431 hasConceptScore W1782523431C106189395 @default.
- W1782523431 hasConceptScore W1782523431C107673813 @default.
- W1782523431 hasConceptScore W1782523431C111472728 @default.
- W1782523431 hasConceptScore W1782523431C119857082 @default.
- W1782523431 hasConceptScore W1782523431C126255220 @default.
- W1782523431 hasConceptScore W1782523431C138885662 @default.
- W1782523431 hasConceptScore W1782523431C14036430 @default.
- W1782523431 hasConceptScore W1782523431C14646407 @default.
- W1782523431 hasConceptScore W1782523431C154945302 @default.
- W1782523431 hasConceptScore W1782523431C159886148 @default.
- W1782523431 hasConceptScore W1782523431C162324750 @default.
- W1782523431 hasConceptScore W1782523431C163836022 @default.
- W1782523431 hasConceptScore W1782523431C17098449 @default.
- W1782523431 hasConceptScore W1782523431C187736073 @default.
- W1782523431 hasConceptScore W1782523431C2776330181 @default.
- W1782523431 hasConceptScore W1782523431C2778049539 @default.
- W1782523431 hasConceptScore W1782523431C2780451532 @default.
- W1782523431 hasConceptScore W1782523431C33923547 @default.
- W1782523431 hasConceptScore W1782523431C41008148 @default.
- W1782523431 hasConceptScore W1782523431C75553542 @default.
- W1782523431 hasConceptScore W1782523431C78458016 @default.
- W1782523431 hasConceptScore W1782523431C86803240 @default.
- W1782523431 hasConceptScore W1782523431C97541855 @default.
- W1782523431 hasConceptScore W1782523431C98763669 @default.
- W1782523431 hasLocation W17825234311 @default.
- W1782523431 hasLocation W17825234312 @default.
- W1782523431 hasLocation W17825234313 @default.
- W1782523431 hasLocation W17825234314 @default.
- W1782523431 hasOpenAccess W1782523431 @default.
- W1782523431 hasPrimaryLocation W17825234311 @default.
- W1782523431 hasRelatedWork W1511927616 @default.
- W1782523431 hasRelatedWork W1515117609 @default.
- W1782523431 hasRelatedWork W2144794447 @default.
- W1782523431 hasRelatedWork W2146763310 @default.
- W1782523431 hasRelatedWork W2156371714 @default.
- W1782523431 hasRelatedWork W2383312578 @default.
- W1782523431 hasRelatedWork W2899657052 @default.
- W1782523431 hasRelatedWork W2937181779 @default.