FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2398693750> ?p ?o ?g. }

• W2398693750 endingPage "243" @default.
• W2398693750 startingPage "217" @default.
• W2398693750 abstract "Different types of dynamics have been studied in repeated game play, and one of them which has received much attention recently consists of those based on “no-regret” algorithms from the area of machine learning. It is known that dynamics based on generic no-regret algorithms may not converge to Nash equilibria in general, but to a larger set of outcomes, namely coarse correlated equilibria. Moreover, convergence results based on generic no-regret algorithms typically use a weaker notion of convergence: the convergence of the average plays instead of the actual plays. Some work has been done showing that when using a specific no-regret algorithm, the well-known multiplicative updates algorithm, convergence of actual plays to equilibria can be shown and better quality of outcomes in terms of the price of anarchy can be reached for atomic congestion games and load balancing games. Are there more cases of natural no-regret dynamics that perform well in suitable classes of games in terms of convergence and quality of outcomes that the dynamics converge to? We answer this question positively in the bulletin-board model by showing that when employing the mirror-descent algorithm, a well-known generic no-regret algorithm, the actual plays converge quickly to equilibria in nonatomic congestion games. This gives rise to a family of algorithms, including the multiplicative updates algorithm and the gradient descent algorithm as well as many others. Furthermore, we show that our dynamics achieves good bounds on the outcome quality in terms of the price-of-anarchy type of measures with two different social costs: the average individual cost and the maximum individual cost. Finally, the bandit model considers a probably more realistic and prevalent setting with only partial information, in which at each time step each player only knows the cost of her own currently played strategy, but not any costs of unplayed strategies. For the class of atomic congestion games, we propose a family of bandit algorithms based on the mirror-descent algorithms previously presented, and show that when each player individually adopts such a bandit algorithm, their joint (mixed) strategy profile quickly converges with implications." @default.
• W2398693750 created "2016-06-24" @default.
• W2398693750 creator A5010588969 @default.
• W2398693750 creator A5031166805 @default.
• W2398693750 date "2016-12-01" @default.
• W2398693750 modified "2023-10-16" @default.
• W2398693750 title "Generalized mirror descents in congestion games" @default.
• W2398693750 cites W1526250527 @default.
• W2398693750 cites W1876716077 @default.
• W2398693750 cites W1971213038 @default.
• W2398693750 cites W1972356540 @default.
• W2398693750 cites W1979357207 @default.
• W2398693750 cites W2015061583 @default.
• W2398693750 cites W2016384870 @default.
• W2398693750 cites W2026177035 @default.
• W2398693750 cites W2034184818 @default.
• W2398693750 cites W2051206974 @default.
• W2398693750 cites W2060113599 @default.
• W2398693750 cites W2074104906 @default.
• W2398693750 cites W2076465870 @default.
• W2398693750 cites W2077902449 @default.
• W2398693750 cites W2083562271 @default.
• W2398693750 cites W2088375330 @default.
• W2398693750 cites W2093825590 @default.
• W2398693750 cites W2106887613 @default.
• W2398693750 cites W2133243407 @default.
• W2398693750 cites W2145297839 @default.
• W2398693750 cites W2154648819 @default.
• W2398693750 cites W4254748829 @default.
• W2398693750 doi "https://doi.org/10.1016/j.artint.2016.09.002" @default.
• W2398693750 hasPublicationYear "2016" @default.
• W2398693750 type Work @default.
• W2398693750 sameAs 2398693750 @default.
• W2398693750 citedByCount "6" @default.
• W2398693750 countsByYear W23986937502019 @default.
• W2398693750 countsByYear W23986937502020 @default.
• W2398693750 countsByYear W23986937502021 @default.
• W2398693750 crossrefType "journal-article" @default.
• W2398693750 hasAuthorship W2398693750A5010588969 @default.
• W2398693750 hasAuthorship W2398693750A5031166805 @default.
• W2398693750 hasBestOaLocation W23986937501 @default.
• W2398693750 hasConcept C119857082 @default.
• W2398693750 hasConcept C126255220 @default.
• W2398693750 hasConcept C126285488 @default.
• W2398693750 hasConcept C134306372 @default.
• W2398693750 hasConcept C144237770 @default.
• W2398693750 hasConcept C153258448 @default.
• W2398693750 hasConcept C154945302 @default.
• W2398693750 hasConcept C162324750 @default.
• W2398693750 hasConcept C188466206 @default.
• W2398693750 hasConcept C2777303404 @default.
• W2398693750 hasConcept C32407928 @default.
• W2398693750 hasConcept C33923547 @default.
• W2398693750 hasConcept C41008148 @default.
• W2398693750 hasConcept C42747912 @default.
• W2398693750 hasConcept C46814582 @default.
• W2398693750 hasConcept C50522688 @default.
• W2398693750 hasConcept C50644808 @default.
• W2398693750 hasConcept C50817715 @default.
• W2398693750 hasConcept C556758197 @default.
• W2398693750 hasConcept C82149807 @default.
• W2398693750 hasConceptScore W2398693750C119857082 @default.
• W2398693750 hasConceptScore W2398693750C126255220 @default.
• W2398693750 hasConceptScore W2398693750C126285488 @default.
• W2398693750 hasConceptScore W2398693750C134306372 @default.
• W2398693750 hasConceptScore W2398693750C144237770 @default.
• W2398693750 hasConceptScore W2398693750C153258448 @default.
• W2398693750 hasConceptScore W2398693750C154945302 @default.
• W2398693750 hasConceptScore W2398693750C162324750 @default.
• W2398693750 hasConceptScore W2398693750C188466206 @default.
• W2398693750 hasConceptScore W2398693750C2777303404 @default.
• W2398693750 hasConceptScore W2398693750C32407928 @default.
• W2398693750 hasConceptScore W2398693750C33923547 @default.
• W2398693750 hasConceptScore W2398693750C41008148 @default.
• W2398693750 hasConceptScore W2398693750C42747912 @default.
• W2398693750 hasConceptScore W2398693750C46814582 @default.
• W2398693750 hasConceptScore W2398693750C50522688 @default.
• W2398693750 hasConceptScore W2398693750C50644808 @default.
• W2398693750 hasConceptScore W2398693750C50817715 @default.
• W2398693750 hasConceptScore W2398693750C556758197 @default.
• W2398693750 hasConceptScore W2398693750C82149807 @default.
• W2398693750 hasFunder F4320321040 @default.
• W2398693750 hasLocation W23986937501 @default.
• W2398693750 hasLocation W23986937502 @default.
• W2398693750 hasOpenAccess W2398693750 @default.
• W2398693750 hasPrimaryLocation W23986937501 @default.
• W2398693750 hasRelatedWork W1517645949 @default.
• W2398693750 hasRelatedWork W1990715672 @default.
• W2398693750 hasRelatedWork W2034184818 @default.
• W2398693750 hasRelatedWork W2133243407 @default.
• W2398693750 hasRelatedWork W2224908015 @default.
• W2398693750 hasRelatedWork W2294025081 @default.
• W2398693750 hasRelatedWork W2398693750 @default.
• W2398693750 hasRelatedWork W2486809103 @default.
• W2398693750 hasRelatedWork W2952551823 @default.
• W2398693750 hasRelatedWork W3092962099 @default.
• W2398693750 hasVolume "241" @default.
• W2398693750 isParatext "false" @default.

• next