Matches in SemOpenAlex for { <https://semopenalex.org/work/W2578423033> ?p ?o ?g. }
- W2578423033 endingPage "1626" @default.
- W2578423033 startingPage "1620" @default.
- W2578423033 abstract "Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong learning settings where the goal is to learn each consecutive task rapidly from as little data as possible. To reduce this burden, we develop a lifelong reinforcement learning method based on coupled dictionary learning that incorporates high-level task descriptors to model the intertask relationships. We show that using task descriptors improves the performance of the learned task policies, providing both theoretical justification for the benefit and empirical demonstration of the improvement across a variety of dynamical control problems. Given only the descriptor for a new task, the lifelong learner is also able to accurately predict the task policy through zero-shot learning using the coupled dictionary, eliminating the need to pause to gather training data before addressing the task." @default.
- W2578423033 created "2017-01-26" @default.
- W2578423033 creator A5020691490 @default.
- W2578423033 creator A5040786186 @default.
- W2578423033 creator A5063634505 @default.
- W2578423033 date "2016-07-09" @default.
- W2578423033 modified "2023-09-26" @default.
- W2578423033 title "Using task features for zero-shot knowledge transfer in lifelong learning" @default.
- W2578423033 cites W1519342765 @default.
- W2578423033 cites W1519626139 @default.
- W2578423033 cites W16827692 @default.
- W2578423033 cites W2012392077 @default.
- W2578423033 cites W2097323375 @default.
- W2578423033 cites W2097381042 @default.
- W2578423033 cites W2099641086 @default.
- W2578423033 cites W2106008664 @default.
- W2578423033 cites W2110994494 @default.
- W2578423033 cites W2119187866 @default.
- W2578423033 cites W2119717200 @default.
- W2578423033 cites W2121058967 @default.
- W2578423033 cites W2130903752 @default.
- W2578423033 cites W2131953535 @default.
- W2578423033 cites W2133013156 @default.
- W2578423033 cites W2134197408 @default.
- W2578423033 cites W2135316123 @default.
- W2578423033 cites W2150295085 @default.
- W2578423033 cites W2152231303 @default.
- W2578423033 cites W2153807823 @default.
- W2578423033 cites W2155027007 @default.
- W2578423033 cites W2235081654 @default.
- W2578423033 cites W2250539671 @default.
- W2578423033 cites W2271262891 @default.
- W2578423033 cites W2294512729 @default.
- W2578423033 cites W2949201716 @default.
- W2578423033 cites W2950190315 @default.
- W2578423033 cites W2950276680 @default.
- W2578423033 cites W35883379 @default.
- W2578423033 cites W652269744 @default.
- W2578423033 hasPublicationYear "2016" @default.
- W2578423033 type Work @default.
- W2578423033 sameAs 2578423033 @default.
- W2578423033 citedByCount "34" @default.
- W2578423033 countsByYear W25784230332016 @default.
- W2578423033 countsByYear W25784230332017 @default.
- W2578423033 countsByYear W25784230332018 @default.
- W2578423033 countsByYear W25784230332019 @default.
- W2578423033 countsByYear W25784230332020 @default.
- W2578423033 countsByYear W25784230332021 @default.
- W2578423033 crossrefType "proceedings-article" @default.
- W2578423033 hasAuthorship W2578423033A5020691490 @default.
- W2578423033 hasAuthorship W2578423033A5040786186 @default.
- W2578423033 hasAuthorship W2578423033A5063634505 @default.
- W2578423033 hasConcept C108771440 @default.
- W2578423033 hasConcept C119857082 @default.
- W2578423033 hasConcept C127413603 @default.
- W2578423033 hasConcept C136197465 @default.
- W2578423033 hasConcept C150899416 @default.
- W2578423033 hasConcept C154945302 @default.
- W2578423033 hasConcept C15744967 @default.
- W2578423033 hasConcept C175154964 @default.
- W2578423033 hasConcept C19417346 @default.
- W2578423033 hasConcept C201995342 @default.
- W2578423033 hasConcept C2775924081 @default.
- W2578423033 hasConcept C2776960227 @default.
- W2578423033 hasConcept C2780451532 @default.
- W2578423033 hasConcept C28006648 @default.
- W2578423033 hasConcept C41008148 @default.
- W2578423033 hasConcept C56739046 @default.
- W2578423033 hasConcept C97541855 @default.
- W2578423033 hasConceptScore W2578423033C108771440 @default.
- W2578423033 hasConceptScore W2578423033C119857082 @default.
- W2578423033 hasConceptScore W2578423033C127413603 @default.
- W2578423033 hasConceptScore W2578423033C136197465 @default.
- W2578423033 hasConceptScore W2578423033C150899416 @default.
- W2578423033 hasConceptScore W2578423033C154945302 @default.
- W2578423033 hasConceptScore W2578423033C15744967 @default.
- W2578423033 hasConceptScore W2578423033C175154964 @default.
- W2578423033 hasConceptScore W2578423033C19417346 @default.
- W2578423033 hasConceptScore W2578423033C201995342 @default.
- W2578423033 hasConceptScore W2578423033C2775924081 @default.
- W2578423033 hasConceptScore W2578423033C2776960227 @default.
- W2578423033 hasConceptScore W2578423033C2780451532 @default.
- W2578423033 hasConceptScore W2578423033C28006648 @default.
- W2578423033 hasConceptScore W2578423033C41008148 @default.
- W2578423033 hasConceptScore W2578423033C56739046 @default.
- W2578423033 hasConceptScore W2578423033C97541855 @default.
- W2578423033 hasOpenAccess W2578423033 @default.
- W2578423033 hasRelatedWork W1519626139 @default.
- W2578423033 hasRelatedWork W2097381042 @default.
- W2578423033 hasRelatedWork W2106008664 @default.
- W2578423033 hasRelatedWork W2109910161 @default.
- W2578423033 hasRelatedWork W2121863487 @default.
- W2578423033 hasRelatedWork W2123024445 @default.
- W2578423033 hasRelatedWork W2134270519 @default.
- W2578423033 hasRelatedWork W2150295085 @default.
- W2578423033 hasRelatedWork W2165698076 @default.
- W2578423033 hasRelatedWork W2169743339 @default.
- W2578423033 hasRelatedWork W2271262891 @default.