FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1569077671> ?p ?o ?g. }

• W1569077671 endingPage "37" @default.
• W1569077671 startingPage "5" @default.
• W1569077671 abstract "The article describes a gradient search based reinforcement learning algorithm for two-player zero-sum games with imperfect information. Simple gradient search may result in oscillation around solution points, a problem similar to the “Crawford puzzle”. To dampen oscillations, the algorithm uses lagging anchors, drawing the strategy state of the players toward a weighted average of earlier strategy states. The algorithm is applicable to games represented in extensive form. We develop methods for sampling the parameter gradient of a player's performance against an opponent, using temporal-difference learning. The algorithm is used successfully for a simplified poker game with infinite sets of pure strategies, and for the air combat game Campaign, using neural nets. We prove exponential convergence of the algorithm for a subset of matrix games." @default.
• W1569077671 created "2016-06-24" @default.
• W1569077671 creator A5040631542 @default.
• W1569077671 date "2002-01-01" @default.
• W1569077671 modified "2023-09-23" @default.
• W1569077671 cites W1485630385 @default.
• W1569077671 cites W1542941925 @default.
• W1569077671 cites W1551740420 @default.
• W1569077671 cites W1564229172 @default.
• W1569077671 cites W1592203014 @default.
• W1569077671 cites W1605188341 @default.
• W1569077671 cites W1661542135 @default.
• W1569077671 cites W1972688571 @default.
• W1569077671 cites W2008519844 @default.
• W1569077671 cites W20481216 @default.
• W1569077671 cites W2048384258 @default.
• W1569077671 cites W2051269406 @default.
• W1569077671 cites W2073540225 @default.
• W1569077671 cites W2086386133 @default.
• W1569077671 cites W2089415692 @default.
• W1569077671 cites W2093277787 @default.
• W1569077671 cites W2100677568 @default.
• W1569077671 cites W2103626435 @default.
• W1569077671 cites W2124503759 @default.
• W1569077671 cites W2138178898 @default.
• W1569077671 cites W2144846366 @default.
• W1569077671 cites W2173567424 @default.
• W1569077671 cites W2266946488 @default.
• W1569077671 cites W2797585760 @default.
• W1569077671 cites W3011120880 @default.
• W1569077671 cites W3198350258 @default.
• W1569077671 cites W47369278 @default.
• W1569077671 cites W624020015 @default.
• W1569077671 cites W2947154587 @default.
• W1569077671 doi "https://doi.org/10.1023/a:1014063505958" @default.
• W1569077671 hasPublicationYear "2002" @default.
• W1569077671 type Work @default.
• W1569077671 sameAs 1569077671 @default.
• W1569077671 citedByCount "14" @default.
• W1569077671 countsByYear W15690776712012 @default.
• W1569077671 countsByYear W15690776712014 @default.
• W1569077671 countsByYear W15690776712015 @default.
• W1569077671 countsByYear W15690776712019 @default.
• W1569077671 crossrefType "journal-article" @default.
• W1569077671 hasAuthorship W1569077671A5040631542 @default.
• W1569077671 hasBestOaLocation W15690776711 @default.
• W1569077671 hasConcept C105795698 @default.
• W1569077671 hasConcept C111472728 @default.
• W1569077671 hasConcept C11413529 @default.
• W1569077671 hasConcept C123676819 @default.
• W1569077671 hasConcept C126255220 @default.
• W1569077671 hasConcept C138885662 @default.
• W1569077671 hasConcept C144237770 @default.
• W1569077671 hasConcept C145071142 @default.
• W1569077671 hasConcept C154945302 @default.
• W1569077671 hasConcept C162324750 @default.
• W1569077671 hasConcept C2776962539 @default.
• W1569077671 hasConcept C2777303404 @default.
• W1569077671 hasConcept C2780586882 @default.
• W1569077671 hasConcept C33923547 @default.
• W1569077671 hasConcept C41008148 @default.
• W1569077671 hasConcept C46814582 @default.
• W1569077671 hasConcept C50522688 @default.
• W1569077671 hasConcept C50644808 @default.
• W1569077671 hasConcept C97541855 @default.
• W1569077671 hasConceptScore W1569077671C105795698 @default.
• W1569077671 hasConceptScore W1569077671C111472728 @default.
• W1569077671 hasConceptScore W1569077671C11413529 @default.
• W1569077671 hasConceptScore W1569077671C123676819 @default.
• W1569077671 hasConceptScore W1569077671C126255220 @default.
• W1569077671 hasConceptScore W1569077671C138885662 @default.
• W1569077671 hasConceptScore W1569077671C144237770 @default.
• W1569077671 hasConceptScore W1569077671C145071142 @default.
• W1569077671 hasConceptScore W1569077671C154945302 @default.
• W1569077671 hasConceptScore W1569077671C162324750 @default.
• W1569077671 hasConceptScore W1569077671C2776962539 @default.
• W1569077671 hasConceptScore W1569077671C2777303404 @default.
• W1569077671 hasConceptScore W1569077671C2780586882 @default.
• W1569077671 hasConceptScore W1569077671C33923547 @default.
• W1569077671 hasConceptScore W1569077671C41008148 @default.
• W1569077671 hasConceptScore W1569077671C46814582 @default.
• W1569077671 hasConceptScore W1569077671C50522688 @default.
• W1569077671 hasConceptScore W1569077671C50644808 @default.
• W1569077671 hasConceptScore W1569077671C97541855 @default.
• W1569077671 hasIssue "1" @default.
• W1569077671 hasLocation W15690776711 @default.
• W1569077671 hasOpenAccess W1569077671 @default.
• W1569077671 hasPrimaryLocation W15690776711 @default.
• W1569077671 hasRelatedWork W1887191277 @default.
• W1569077671 hasRelatedWork W2291986326 @default.
• W1569077671 hasRelatedWork W260766989 @default.
• W1569077671 hasRelatedWork W2959276766 @default.
• W1569077671 hasRelatedWork W3044994704 @default.
• W1569077671 hasRelatedWork W3097986043 @default.
• W1569077671 hasRelatedWork W3139193008 @default.
• W1569077671 hasRelatedWork W3146136970 @default.
• W1569077671 hasRelatedWork W4206669594 @default.
• W1569077671 hasRelatedWork W4295941380 @default.

• next