Matches in SemOpenAlex for { <https://semopenalex.org/work/W2106975967> ?p ?o ?g. }
- W2106975967 endingPage "1086" @default.
- W2106975967 startingPage "1078" @default.
- W2106975967 abstract "Sequential decision-making with multiple agents and imperfect information is commonly modeled as an extensive game. One efficient method for computing Nash equilibria in large, zero-sum, imperfect information games is counterfactual regret minimization (CFR). In the domain of poker, CFR has proven effective, particularly when using a domain-specific augmentation involving chance outcome sampling. In this paper, we describe a general family of domain-independent CFR sample-based algorithms called Monte Carlo counterfactual regret minimization (MCCFR) of which the original and poker-specific versions are special cases. We start by showing that MCCFR performs the same regret updates as CFR on expectation. Then, we introduce two sampling schemes: outcome sampling and external sampling, showing that both have bounded overall regret with high probability. Thus, they can compute an approximate equilibrium using self-play. Finally, we prove a new tighter bound on the regret for the original CFR algorithm and relate this new bound to MCCFR's bounds. We show empirically that, although the sample-based algorithms require more iterations, their lower cost per iteration can lead to dramatically faster convergence in various games." @default.
- W2106975967 created "2016-06-24" @default.
- W2106975967 creator A5045201269 @default.
- W2106975967 creator A5049659586 @default.
- W2106975967 creator A5074900890 @default.
- W2106975967 creator A5081163135 @default.
- W2106975967 date "2009-12-07" @default.
- W2106975967 modified "2023-09-29" @default.
- W2106975967 title "Monte Carlo Sampling for Regret Minimization in Extensive Games" @default.
- W2106975967 cites W1510190958 @default.
- W2106975967 cites W1581842928 @default.
- W2106975967 cites W1980717955 @default.
- W2106975967 cites W1982813377 @default.
- W2106975967 cites W2047363889 @default.
- W2106975967 cites W2103315867 @default.
- W2106975967 cites W2109100253 @default.
- W2106975967 cites W2116067849 @default.
- W2106975967 cites W2126776273 @default.
- W2106975967 cites W2131867500 @default.
- W2106975967 cites W292627938 @default.
- W2106975967 cites W3207306951 @default.
- W2106975967 doi "https://doi.org/10.7939/r3319s48q" @default.
- W2106975967 hasPublicationYear "2009" @default.
- W2106975967 type Work @default.
- W2106975967 sameAs 2106975967 @default.
- W2106975967 citedByCount "137" @default.
- W2106975967 countsByYear W21069759672012 @default.
- W2106975967 countsByYear W21069759672013 @default.
- W2106975967 countsByYear W21069759672014 @default.
- W2106975967 countsByYear W21069759672015 @default.
- W2106975967 countsByYear W21069759672016 @default.
- W2106975967 countsByYear W21069759672017 @default.
- W2106975967 countsByYear W21069759672018 @default.
- W2106975967 countsByYear W21069759672019 @default.
- W2106975967 countsByYear W21069759672020 @default.
- W2106975967 countsByYear W21069759672021 @default.
- W2106975967 countsByYear W21069759672022 @default.
- W2106975967 crossrefType "proceedings-article" @default.
- W2106975967 hasAuthorship W2106975967A5045201269 @default.
- W2106975967 hasAuthorship W2106975967A5049659586 @default.
- W2106975967 hasAuthorship W2106975967A5074900890 @default.
- W2106975967 hasAuthorship W2106975967A5081163135 @default.
- W2106975967 hasConcept C105795698 @default.
- W2106975967 hasConcept C106131492 @default.
- W2106975967 hasConcept C108650721 @default.
- W2106975967 hasConcept C111472728 @default.
- W2106975967 hasConcept C11413529 @default.
- W2106975967 hasConcept C119857082 @default.
- W2106975967 hasConcept C123676819 @default.
- W2106975967 hasConcept C126255220 @default.
- W2106975967 hasConcept C134306372 @default.
- W2106975967 hasConcept C138885662 @default.
- W2106975967 hasConcept C140779682 @default.
- W2106975967 hasConcept C144237770 @default.
- W2106975967 hasConcept C148220186 @default.
- W2106975967 hasConcept C19499675 @default.
- W2106975967 hasConcept C31972630 @default.
- W2106975967 hasConcept C33923547 @default.
- W2106975967 hasConcept C34388435 @default.
- W2106975967 hasConcept C36503486 @default.
- W2106975967 hasConcept C41008148 @default.
- W2106975967 hasConcept C46814582 @default.
- W2106975967 hasConcept C50817715 @default.
- W2106975967 hasConcept C52740198 @default.
- W2106975967 hasConceptScore W2106975967C105795698 @default.
- W2106975967 hasConceptScore W2106975967C106131492 @default.
- W2106975967 hasConceptScore W2106975967C108650721 @default.
- W2106975967 hasConceptScore W2106975967C111472728 @default.
- W2106975967 hasConceptScore W2106975967C11413529 @default.
- W2106975967 hasConceptScore W2106975967C119857082 @default.
- W2106975967 hasConceptScore W2106975967C123676819 @default.
- W2106975967 hasConceptScore W2106975967C126255220 @default.
- W2106975967 hasConceptScore W2106975967C134306372 @default.
- W2106975967 hasConceptScore W2106975967C138885662 @default.
- W2106975967 hasConceptScore W2106975967C140779682 @default.
- W2106975967 hasConceptScore W2106975967C144237770 @default.
- W2106975967 hasConceptScore W2106975967C148220186 @default.
- W2106975967 hasConceptScore W2106975967C19499675 @default.
- W2106975967 hasConceptScore W2106975967C31972630 @default.
- W2106975967 hasConceptScore W2106975967C33923547 @default.
- W2106975967 hasConceptScore W2106975967C34388435 @default.
- W2106975967 hasConceptScore W2106975967C36503486 @default.
- W2106975967 hasConceptScore W2106975967C41008148 @default.
- W2106975967 hasConceptScore W2106975967C46814582 @default.
- W2106975967 hasConceptScore W2106975967C50817715 @default.
- W2106975967 hasConceptScore W2106975967C52740198 @default.
- W2106975967 hasLocation W21069759671 @default.
- W2106975967 hasOpenAccess W2106975967 @default.
- W2106975967 hasPrimaryLocation W21069759671 @default.
- W2106975967 hasRelatedWork W1625390266 @default.
- W2106975967 hasRelatedWork W1664963465 @default.
- W2106975967 hasRelatedWork W193176855 @default.
- W2106975967 hasRelatedWork W1980392196 @default.
- W2106975967 hasRelatedWork W2006791053 @default.
- W2106975967 hasRelatedWork W2086312499 @default.
- W2106975967 hasRelatedWork W2103315867 @default.
- W2106975967 hasRelatedWork W2109100253 @default.
- W2106975967 hasRelatedWork W2121513215 @default.