FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1526641569> ?p ?o ?g. }

• W1526641569 endingPage "1269" @default.
• W1526641569 startingPage "1246" @default.
• W1526641569 abstract "Classification-based reinforcement learning (RL) methods have recently been pro- posed as an alternative to the traditional value-function based methods. These methods use a classifier to represent a policy, where the input (features) to the classifier is the state and the output (class label) for that state is the desired action. The reinforcement-learning community knows that focusing on more important states can lead to improved performance. In this paper, we investigate the idea of focused learning in the context of classification-based RL. Specifically, we define a useful notation of state importance, which we use to prove rigorous bounds on policy loss. Furthermore, we show that a classification-based RL agent may behave arbitrarily poorly if it treats all states as equally important." @default.
• W1526641569 created "2016-06-24" @default.
• W1526641569 creator A5027200864 @default.
• W1526641569 creator A5054850777 @default.
• W1526641569 creator A5076298832 @default.
• W1526641569 date "2007-01-01" @default.
• W1526641569 modified "2023-09-27" @default.
• W1526641569 title "Focus of Attention in Reinforcement Learning" @default.
• W1526641569 cites W1490760466 @default.
• W1526641569 cites W1491843047 @default.
• W1526641569 cites W1499408472 @default.
• W1526641569 cites W1512919909 @default.
• W1526641569 cites W1560561838 @default.
• W1526641569 cites W1575592356 @default.
• W1526641569 cites W1576452626 @default.
• W1526641569 cites W1585546214 @default.
• W1526641569 cites W1601974704 @default.
• W1526641569 cites W1625390266 @default.
• W1526641569 cites W1654728867 @default.
• W1526641569 cites W1681299129 @default.
• W1526641569 cites W1819386543 @default.
• W1526641569 cites W1920296779 @default.
• W1526641569 cites W1949804828 @default.
• W1526641569 cites W2009533501 @default.
• W1526641569 cites W2028145673 @default.
• W1526641569 cites W2037199950 @default.
• W1526641569 cites W2039439610 @default.
• W1526641569 cites W2048226872 @default.
• W1526641569 cites W2100677568 @default.
• W1526641569 cites W2103626435 @default.
• W1526641569 cites W2106451198 @default.
• W1526641569 cites W2108734173 @default.
• W1526641569 cites W2117341272 @default.
• W1526641569 cites W2119567691 @default.
• W1526641569 cites W2119717200 @default.
• W1526641569 cites W2121863487 @default.
• W1526641569 cites W2128477394 @default.
• W1526641569 cites W2128547596 @default.
• W1526641569 cites W2128619633 @default.
• W1526641569 cites W2130906191 @default.
• W1526641569 cites W2134289401 @default.
• W1526641569 cites W2135997697 @default.
• W1526641569 cites W2141559645 @default.
• W1526641569 cites W2143490508 @default.
• W1526641569 cites W2155027007 @default.
• W1526641569 cites W2161521419 @default.
• W1526641569 cites W2799061466 @default.
• W1526641569 cites W3011120880 @default.
• W1526641569 cites W354571 @default.
• W1526641569 cites W2131600418 @default.
• W1526641569 doi "https://doi.org/10.7939/r31g0hx9n" @default.
• W1526641569 hasPublicationYear "2007" @default.
• W1526641569 type Work @default.
• W1526641569 sameAs 1526641569 @default.
• W1526641569 citedByCount "9" @default.
• W1526641569 countsByYear W15266415692014 @default.
• W1526641569 countsByYear W15266415692016 @default.
• W1526641569 countsByYear W15266415692017 @default.
• W1526641569 countsByYear W15266415692019 @default.
• W1526641569 crossrefType "journal-article" @default.
• W1526641569 hasAuthorship W1526641569A5027200864 @default.
• W1526641569 hasAuthorship W1526641569A5054850777 @default.
• W1526641569 hasAuthorship W1526641569A5076298832 @default.
• W1526641569 hasConcept C119857082 @default.
• W1526641569 hasConcept C154945302 @default.
• W1526641569 hasConcept C199190896 @default.
• W1526641569 hasConcept C2779436431 @default.
• W1526641569 hasConcept C33923547 @default.
• W1526641569 hasConcept C41008148 @default.
• W1526641569 hasConcept C45357846 @default.
• W1526641569 hasConcept C94375191 @default.
• W1526641569 hasConcept C95623464 @default.
• W1526641569 hasConcept C97541855 @default.
• W1526641569 hasConceptScore W1526641569C119857082 @default.
• W1526641569 hasConceptScore W1526641569C154945302 @default.
• W1526641569 hasConceptScore W1526641569C199190896 @default.
• W1526641569 hasConceptScore W1526641569C2779436431 @default.
• W1526641569 hasConceptScore W1526641569C33923547 @default.
• W1526641569 hasConceptScore W1526641569C41008148 @default.
• W1526641569 hasConceptScore W1526641569C45357846 @default.
• W1526641569 hasConceptScore W1526641569C94375191 @default.
• W1526641569 hasConceptScore W1526641569C95623464 @default.
• W1526641569 hasConceptScore W1526641569C97541855 @default.
• W1526641569 hasLocation W15266415691 @default.
• W1526641569 hasOpenAccess W1526641569 @default.
• W1526641569 hasPrimaryLocation W15266415691 @default.
• W1526641569 hasRelatedWork W1884070896 @default.
• W1526641569 hasRelatedWork W2037199950 @default.
• W1526641569 hasRelatedWork W2072931156 @default.
• W1526641569 hasRelatedWork W2121863487 @default.
• W1526641569 hasRelatedWork W2128547596 @default.
• W1526641569 hasRelatedWork W2129297552 @default.
• W1526641569 hasRelatedWork W2130005627 @default.
• W1526641569 hasRelatedWork W2134289401 @default.
• W1526641569 hasRelatedWork W2154023516 @default.
• W1526641569 hasRelatedWork W2165060096 @default.
• W1526641569 hasRelatedWork W2165421048 @default.
• W1526641569 hasRelatedWork W2892990871 @default.

• next