Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952527153> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2952527153 abstract "We propose a novel online learning method for minimizing regret in large extensive-form games. The approach learns a function approximator online to estimate the regret for choosing a particular action. A no-regret algorithm uses these estimates in place of the true regrets to define a sequence of policies. We prove the approach sound by providing a bound relating the quality of the function approximation and regret of the algorithm. A corollary being that the method is guaranteed to converge to a Nash equilibrium in self-play so long as the regrets are ultimately realizable by the function approximator. Our technique can be understood as a principled generalization of existing work on abstraction in large games; in our work, both the abstraction as well as the equilibrium are learned during self-play. We demonstrate empirically the method achieves higher quality strategies than state-of-the-art abstraction techniques given the same resources." @default.
- W2952527153 created "2019-06-27" @default.
- W2952527153 creator A5034064327 @default.
- W2952527153 creator A5045201269 @default.
- W2952527153 creator A5046207547 @default.
- W2952527153 creator A5081163135 @default.
- W2952527153 date "2014-11-28" @default.
- W2952527153 modified "2023-09-27" @default.
- W2952527153 title "Solving Games with Functional Regret Estimation" @default.
- W2952527153 cites W1528107507 @default.
- W2952527153 cites W1551269584 @default.
- W2952527153 cites W193176855 @default.
- W2952527153 cites W2014482607 @default.
- W2952527153 cites W2098111478 @default.
- W2952527153 cites W2103315867 @default.
- W2952527153 cites W2106975967 @default.
- W2952527153 cites W2123018439 @default.
- W2952527153 cites W2126776273 @default.
- W2952527153 cites W2158973351 @default.
- W2952527153 cites W2168356773 @default.
- W2952527153 cites W2962957031 @default.
- W2952527153 cites W2522081855 @default.
- W2952527153 hasPublicationYear "2014" @default.
- W2952527153 type Work @default.
- W2952527153 sameAs 2952527153 @default.
- W2952527153 citedByCount "1" @default.
- W2952527153 countsByYear W29525271532020 @default.
- W2952527153 crossrefType "posted-content" @default.
- W2952527153 hasAuthorship W2952527153A5034064327 @default.
- W2952527153 hasAuthorship W2952527153A5045201269 @default.
- W2952527153 hasAuthorship W2952527153A5046207547 @default.
- W2952527153 hasAuthorship W2952527153A5081163135 @default.
- W2952527153 hasConcept C111472728 @default.
- W2952527153 hasConcept C118615104 @default.
- W2952527153 hasConcept C119857082 @default.
- W2952527153 hasConcept C124304363 @default.
- W2952527153 hasConcept C126255220 @default.
- W2952527153 hasConcept C134306372 @default.
- W2952527153 hasConcept C138885662 @default.
- W2952527153 hasConcept C14036430 @default.
- W2952527153 hasConcept C144237770 @default.
- W2952527153 hasConcept C177148314 @default.
- W2952527153 hasConcept C2778112365 @default.
- W2952527153 hasConcept C2779530757 @default.
- W2952527153 hasConcept C2780012671 @default.
- W2952527153 hasConcept C33923547 @default.
- W2952527153 hasConcept C41008148 @default.
- W2952527153 hasConcept C46814582 @default.
- W2952527153 hasConcept C50817715 @default.
- W2952527153 hasConcept C54355233 @default.
- W2952527153 hasConcept C78458016 @default.
- W2952527153 hasConcept C86803240 @default.
- W2952527153 hasConceptScore W2952527153C111472728 @default.
- W2952527153 hasConceptScore W2952527153C118615104 @default.
- W2952527153 hasConceptScore W2952527153C119857082 @default.
- W2952527153 hasConceptScore W2952527153C124304363 @default.
- W2952527153 hasConceptScore W2952527153C126255220 @default.
- W2952527153 hasConceptScore W2952527153C134306372 @default.
- W2952527153 hasConceptScore W2952527153C138885662 @default.
- W2952527153 hasConceptScore W2952527153C14036430 @default.
- W2952527153 hasConceptScore W2952527153C144237770 @default.
- W2952527153 hasConceptScore W2952527153C177148314 @default.
- W2952527153 hasConceptScore W2952527153C2778112365 @default.
- W2952527153 hasConceptScore W2952527153C2779530757 @default.
- W2952527153 hasConceptScore W2952527153C2780012671 @default.
- W2952527153 hasConceptScore W2952527153C33923547 @default.
- W2952527153 hasConceptScore W2952527153C41008148 @default.
- W2952527153 hasConceptScore W2952527153C46814582 @default.
- W2952527153 hasConceptScore W2952527153C50817715 @default.
- W2952527153 hasConceptScore W2952527153C54355233 @default.
- W2952527153 hasConceptScore W2952527153C78458016 @default.
- W2952527153 hasConceptScore W2952527153C86803240 @default.
- W2952527153 hasLocation W29525271531 @default.
- W2952527153 hasOpenAccess W2952527153 @default.
- W2952527153 hasPrimaryLocation W29525271531 @default.
- W2952527153 hasRelatedWork W1726776292 @default.
- W2952527153 hasRelatedWork W1874758362 @default.
- W2952527153 hasRelatedWork W2103315867 @default.
- W2952527153 hasRelatedWork W2138627397 @default.
- W2952527153 hasRelatedWork W2168509539 @default.
- W2952527153 hasRelatedWork W2189505099 @default.
- W2952527153 hasRelatedWork W2396453985 @default.
- W2952527153 hasRelatedWork W2465818302 @default.
- W2952527153 hasRelatedWork W2514312096 @default.
- W2952527153 hasRelatedWork W2889616780 @default.
- W2952527153 hasRelatedWork W2901492934 @default.
- W2952527153 hasRelatedWork W2920763178 @default.
- W2952527153 hasRelatedWork W2951784412 @default.
- W2952527153 hasRelatedWork W2962910243 @default.
- W2952527153 hasRelatedWork W2963364412 @default.
- W2952527153 hasRelatedWork W3083708002 @default.
- W2952527153 hasRelatedWork W3096083037 @default.
- W2952527153 hasRelatedWork W3108314947 @default.
- W2952527153 hasRelatedWork W3174252005 @default.
- W2952527153 hasRelatedWork W3176372150 @default.
- W2952527153 isParatext "false" @default.
- W2952527153 isRetracted "false" @default.
- W2952527153 magId "2952527153" @default.
- W2952527153 workType "article" @default.