Matches in SemOpenAlex for { <https://semopenalex.org/work/W2159849946> ?p ?o ?g. }
- W2159849946 endingPage "998" @default.
- W2159849946 startingPage "990" @default.
- W2159849946 abstract "We consider the problem of learning models of options for real-time abstract planning, in the setting where reward functions can be specified at any time and their expected returns must be efficiently computed. We introduce a new model for an option that is independent of any reward function, called the universal option model (UOM). We prove that the UOM of an option can construct a traditional option model given a reward function, and also supports efficient computation of the option-conditional return. We extend the UOM to linear function approximation, and we show the UOM gives the TD solution of option returns and the value function of a policy over options. We provide a stochastic approximation algorithm for incrementally learning UOMs from data and prove its consistency. We demonstrate our method in two domains. The first domain is a real-time strategy game, where the controller must select the best game unit to accomplish a dynamically-specified task. The second domain is article recommendation, where each user query defines a new reward function and an article's relevance is the expected return from following a policy that follows the citations between articles. Our experiments show that UOMs are substantially more efficient than previously known methods for evaluating option returns and policies over options." @default.
- W2159849946 created "2016-06-24" @default.
- W2159849946 creator A5004923102 @default.
- W2159849946 creator A5038163398 @default.
- W2159849946 creator A5050876115 @default.
- W2159849946 creator A5054065284 @default.
- W2159849946 creator A5069856068 @default.
- W2159849946 date "2014-12-08" @default.
- W2159849946 modified "2023-10-05" @default.
- W2159849946 title "Universal Option Models" @default.
- W2159849946 cites W1515851193 @default.
- W2159849946 cites W1576452626 @default.
- W2159849946 cites W1585861384 @default.
- W2159849946 cites W1854214752 @default.
- W2159849946 cites W194754089 @default.
- W2159849946 cites W2022322548 @default.
- W2159849946 cites W2061562262 @default.
- W2159849946 cites W2096041903 @default.
- W2159849946 cites W2109910161 @default.
- W2159849946 cites W2121863487 @default.
- W2159849946 cites W2126217565 @default.
- W2159849946 cites W2134491302 @default.
- W2159849946 cites W2165131254 @default.
- W2159849946 cites W2912453235 @default.
- W2159849946 hasPublicationYear "2014" @default.
- W2159849946 type Work @default.
- W2159849946 sameAs 2159849946 @default.
- W2159849946 citedByCount "16" @default.
- W2159849946 countsByYear W21598499462015 @default.
- W2159849946 countsByYear W21598499462016 @default.
- W2159849946 countsByYear W21598499462017 @default.
- W2159849946 countsByYear W21598499462019 @default.
- W2159849946 countsByYear W21598499462020 @default.
- W2159849946 countsByYear W21598499462021 @default.
- W2159849946 crossrefType "proceedings-article" @default.
- W2159849946 hasAuthorship W2159849946A5004923102 @default.
- W2159849946 hasAuthorship W2159849946A5038163398 @default.
- W2159849946 hasAuthorship W2159849946A5050876115 @default.
- W2159849946 hasAuthorship W2159849946A5054065284 @default.
- W2159849946 hasAuthorship W2159849946A5069856068 @default.
- W2159849946 hasConcept C105795698 @default.
- W2159849946 hasConcept C11413529 @default.
- W2159849946 hasConcept C126255220 @default.
- W2159849946 hasConcept C134306372 @default.
- W2159849946 hasConcept C14036430 @default.
- W2159849946 hasConcept C154945302 @default.
- W2159849946 hasConcept C158154518 @default.
- W2159849946 hasConcept C162324750 @default.
- W2159849946 hasConcept C17744445 @default.
- W2159849946 hasConcept C187736073 @default.
- W2159849946 hasConcept C199360897 @default.
- W2159849946 hasConcept C199539241 @default.
- W2159849946 hasConcept C2776436953 @default.
- W2159849946 hasConcept C2780451532 @default.
- W2159849946 hasConcept C2780801425 @default.
- W2159849946 hasConcept C2781249084 @default.
- W2159849946 hasConcept C33923547 @default.
- W2159849946 hasConcept C36503486 @default.
- W2159849946 hasConcept C41008148 @default.
- W2159849946 hasConcept C45374587 @default.
- W2159849946 hasConcept C78458016 @default.
- W2159849946 hasConcept C86803240 @default.
- W2159849946 hasConceptScore W2159849946C105795698 @default.
- W2159849946 hasConceptScore W2159849946C11413529 @default.
- W2159849946 hasConceptScore W2159849946C126255220 @default.
- W2159849946 hasConceptScore W2159849946C134306372 @default.
- W2159849946 hasConceptScore W2159849946C14036430 @default.
- W2159849946 hasConceptScore W2159849946C154945302 @default.
- W2159849946 hasConceptScore W2159849946C158154518 @default.
- W2159849946 hasConceptScore W2159849946C162324750 @default.
- W2159849946 hasConceptScore W2159849946C17744445 @default.
- W2159849946 hasConceptScore W2159849946C187736073 @default.
- W2159849946 hasConceptScore W2159849946C199360897 @default.
- W2159849946 hasConceptScore W2159849946C199539241 @default.
- W2159849946 hasConceptScore W2159849946C2776436953 @default.
- W2159849946 hasConceptScore W2159849946C2780451532 @default.
- W2159849946 hasConceptScore W2159849946C2780801425 @default.
- W2159849946 hasConceptScore W2159849946C2781249084 @default.
- W2159849946 hasConceptScore W2159849946C33923547 @default.
- W2159849946 hasConceptScore W2159849946C36503486 @default.
- W2159849946 hasConceptScore W2159849946C41008148 @default.
- W2159849946 hasConceptScore W2159849946C45374587 @default.
- W2159849946 hasConceptScore W2159849946C78458016 @default.
- W2159849946 hasConceptScore W2159849946C86803240 @default.
- W2159849946 hasLocation W21598499461 @default.
- W2159849946 hasOpenAccess W2159849946 @default.
- W2159849946 hasPrimaryLocation W21598499461 @default.
- W2159849946 hasRelatedWork W1515851193 @default.
- W2159849946 hasRelatedWork W1536990779 @default.
- W2159849946 hasRelatedWork W2056354534 @default.
- W2159849946 hasRelatedWork W2100677568 @default.
- W2159849946 hasRelatedWork W2109910161 @default.
- W2159849946 hasRelatedWork W2111625828 @default.
- W2159849946 hasRelatedWork W2119567691 @default.
- W2159849946 hasRelatedWork W2121517924 @default.
- W2159849946 hasRelatedWork W2121863487 @default.
- W2159849946 hasRelatedWork W2132622533 @default.
- W2159849946 hasRelatedWork W2139612737 @default.