Matches in SemOpenAlex for { <https://semopenalex.org/work/W2122668024> ?p ?o ?g. }
- W2122668024 endingPage "238" @default.
- W2122668024 startingPage "221" @default.
- W2122668024 abstract "We describe how an agent can dynamically and incrementally determine the structure of a value function from background knowledge as a side effect of problem solving. The agent determines the value function as it performs the task, using background knowledge in novel situations to compute an expected value for decision making. That expected value becomes the initial estimate of the value function, and the features tested by the background knowledge form the structure of the value function. This approach is implemented in Soar, using its existing mechanisms, relying on its preference-based decision-making, impasse-driven subgoaling, explanation-based rulelearning (chunking), and reinforcement learning. We evaluate this approach on a multiplayer dice game in which three different types of background knowledge are used." @default.
- W2122668024 created "2016-06-24" @default.
- W2122668024 creator A5013253260 @default.
- W2122668024 creator A5050664411 @default.
- W2122668024 creator A5061159721 @default.
- W2122668024 date "2012-01-01" @default.
- W2122668024 modified "2023-09-26" @default.
- W2122668024 title "Online Determination of Value-Function Structure and Action-value Estimates for Reinforcement Learning in a Cognitive Architecture" @default.
- W2122668024 cites W118404535 @default.
- W2122668024 cites W1258105458 @default.
- W2122668024 cites W1486330393 @default.
- W2122668024 cites W1487478277 @default.
- W2122668024 cites W152570004 @default.
- W2122668024 cites W1552830313 @default.
- W2122668024 cites W1777239053 @default.
- W2122668024 cites W1970906492 @default.
- W2122668024 cites W2013939223 @default.
- W2122668024 cites W2053353957 @default.
- W2122668024 cites W2057113818 @default.
- W2122668024 cites W2101602574 @default.
- W2122668024 cites W2110927808 @default.
- W2122668024 cites W2129442128 @default.
- W2122668024 cites W2140256637 @default.
- W2122668024 cites W2140964982 @default.
- W2122668024 cites W2163445345 @default.
- W2122668024 cites W2200902145 @default.
- W2122668024 cites W2493514692 @default.
- W2122668024 cites W2610302167 @default.
- W2122668024 cites W2911283634 @default.
- W2122668024 cites W2914656440 @default.
- W2122668024 cites W3011120880 @default.
- W2122668024 cites W3139377883 @default.
- W2122668024 cites W419646410 @default.
- W2122668024 cites W90468634 @default.
- W2122668024 hasPublicationYear "2012" @default.
- W2122668024 type Work @default.
- W2122668024 sameAs 2122668024 @default.
- W2122668024 citedByCount "2" @default.
- W2122668024 countsByYear W21226680242013 @default.
- W2122668024 countsByYear W21226680242014 @default.
- W2122668024 crossrefType "journal-article" @default.
- W2122668024 hasAuthorship W2122668024A5013253260 @default.
- W2122668024 hasAuthorship W2122668024A5050664411 @default.
- W2122668024 hasAuthorship W2122668024A5061159721 @default.
- W2122668024 hasConcept C105795698 @default.
- W2122668024 hasConcept C119857082 @default.
- W2122668024 hasConcept C126255220 @default.
- W2122668024 hasConcept C14036430 @default.
- W2122668024 hasConcept C144133560 @default.
- W2122668024 hasConcept C14646407 @default.
- W2122668024 hasConcept C154945302 @default.
- W2122668024 hasConcept C162853370 @default.
- W2122668024 hasConcept C17305859 @default.
- W2122668024 hasConcept C203357204 @default.
- W2122668024 hasConcept C22029948 @default.
- W2122668024 hasConcept C2776291640 @default.
- W2122668024 hasConcept C33923547 @default.
- W2122668024 hasConcept C41008148 @default.
- W2122668024 hasConcept C4216890 @default.
- W2122668024 hasConcept C78458016 @default.
- W2122668024 hasConcept C86803240 @default.
- W2122668024 hasConcept C89249532 @default.
- W2122668024 hasConcept C97541855 @default.
- W2122668024 hasConceptScore W2122668024C105795698 @default.
- W2122668024 hasConceptScore W2122668024C119857082 @default.
- W2122668024 hasConceptScore W2122668024C126255220 @default.
- W2122668024 hasConceptScore W2122668024C14036430 @default.
- W2122668024 hasConceptScore W2122668024C144133560 @default.
- W2122668024 hasConceptScore W2122668024C14646407 @default.
- W2122668024 hasConceptScore W2122668024C154945302 @default.
- W2122668024 hasConceptScore W2122668024C162853370 @default.
- W2122668024 hasConceptScore W2122668024C17305859 @default.
- W2122668024 hasConceptScore W2122668024C203357204 @default.
- W2122668024 hasConceptScore W2122668024C22029948 @default.
- W2122668024 hasConceptScore W2122668024C2776291640 @default.
- W2122668024 hasConceptScore W2122668024C33923547 @default.
- W2122668024 hasConceptScore W2122668024C41008148 @default.
- W2122668024 hasConceptScore W2122668024C4216890 @default.
- W2122668024 hasConceptScore W2122668024C78458016 @default.
- W2122668024 hasConceptScore W2122668024C86803240 @default.
- W2122668024 hasConceptScore W2122668024C89249532 @default.
- W2122668024 hasConceptScore W2122668024C97541855 @default.
- W2122668024 hasLocation W21226680241 @default.
- W2122668024 hasOpenAccess W2122668024 @default.
- W2122668024 hasPrimaryLocation W21226680241 @default.
- W2122668024 hasRelatedWork W143164768 @default.
- W2122668024 hasRelatedWork W1533269661 @default.
- W2122668024 hasRelatedWork W2042357378 @default.
- W2122668024 hasRelatedWork W2056107474 @default.
- W2122668024 hasRelatedWork W2099945315 @default.
- W2122668024 hasRelatedWork W2136719210 @default.
- W2122668024 hasRelatedWork W2154023516 @default.
- W2122668024 hasRelatedWork W2159880874 @default.
- W2122668024 hasRelatedWork W2888519432 @default.
- W2122668024 hasRelatedWork W2891573147 @default.
- W2122668024 hasRelatedWork W2892990871 @default.
- W2122668024 hasRelatedWork W2915060045 @default.
- W2122668024 hasRelatedWork W2964296021 @default.