Matches in SemOpenAlex for { <https://semopenalex.org/work/W77704268> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W77704268 abstract "In 2000, Hart and Mas-Colell introduced the important game-theoretic algorithm of regret matching. Players reach equilibrium play by tracking regrets for past plays, making future plays proportional to positive regrets. The technique is not only simple and intuitive; it has sparked a revolution in computer game play of some of the most difficult bluffing games, including clear domination of annual computer poker competitions. Since the algorithm is relatively recent, there are few curricular materials available to introduce regret-based algorithms to the next generation of researchers and practitioners in this area. These materials represent a modest first step towards making recent innovations more accessible to advanced Computer Science undergraduates, graduate students, interested researchers, and ambitious practitioners. In Section 2, we introduce the concept of player regret, describe the regret-matching algorithm, present a rock-paper-scissors worked example in the literate programming style, and suggest related exercises. Counterfactual Regret Minimization (CFR) is introduced in Section 3 with a worked example solving Kuhn Poker. Supporting code is provided for a substantive CFR exercise computing optimal play for 1-die-versus-1-die Dudo. In Section 4, we briefly mention means of “cleaning” approximately optimal computed policies, which can in many cases improve results. Section 5 covers an advanced application of CFR to games with repeated states (e.g. through imperfect recall abstraction) that can reduce computational complexity of a CFR training iteration from exponential to linear. Here, we use our independently devised game of Liar Die to demonstrate application of the algorithm. We then suggest that the reader apply the technique to 1-die-versus-1-die Dudo with a memory of 3 claims. In Section 6, we briefly discuss an open research problem: Among possible equilibrium strategies, how do we compute one that optimally exploits opponent errors? The reader is invited to modify our Liar Die example code to so as to gain insight to this interesting problem. Finally, in Section 7, we suggest further challenge problems and paths for continued learning." @default.
- W77704268 created "2016-06-24" @default.
- W77704268 creator A5028487946 @default.
- W77704268 creator A5049659586 @default.
- W77704268 date "2013-01-01" @default.
- W77704268 modified "2023-09-26" @default.
- W77704268 title "An Introduction to Counterfactual Regret Minimization" @default.
- W77704268 cites W1482508514 @default.
- W77704268 cites W1847992018 @default.
- W77704268 cites W2006794473 @default.
- W77704268 cites W2018840192 @default.
- W77704268 cites W2103315867 @default.
- W77704268 cites W2106975967 @default.
- W77704268 cites W2111589951 @default.
- W77704268 cites W2126776273 @default.
- W77704268 cites W2153816030 @default.
- W77704268 cites W2188529601 @default.
- W77704268 cites W2395326189 @default.
- W77704268 cites W2950376443 @default.
- W77704268 cites W3207306951 @default.
- W77704268 cites W91792424 @default.
- W77704268 hasPublicationYear "2013" @default.
- W77704268 type Work @default.
- W77704268 sameAs 77704268 @default.
- W77704268 citedByCount "13" @default.
- W77704268 countsByYear W777042682014 @default.
- W77704268 countsByYear W777042682017 @default.
- W77704268 countsByYear W777042682018 @default.
- W77704268 countsByYear W777042682019 @default.
- W77704268 countsByYear W777042682020 @default.
- W77704268 countsByYear W777042682021 @default.
- W77704268 crossrefType "journal-article" @default.
- W77704268 hasAuthorship W77704268A5028487946 @default.
- W77704268 hasAuthorship W77704268A5049659586 @default.
- W77704268 hasConcept C105795698 @default.
- W77704268 hasConcept C108650721 @default.
- W77704268 hasConcept C111472728 @default.
- W77704268 hasConcept C119857082 @default.
- W77704268 hasConcept C124304363 @default.
- W77704268 hasConcept C138885662 @default.
- W77704268 hasConcept C144237770 @default.
- W77704268 hasConcept C15744967 @default.
- W77704268 hasConcept C165064840 @default.
- W77704268 hasConcept C33923547 @default.
- W77704268 hasConcept C41008148 @default.
- W77704268 hasConcept C42475967 @default.
- W77704268 hasConcept C50817715 @default.
- W77704268 hasConcept C77805123 @default.
- W77704268 hasConceptScore W77704268C105795698 @default.
- W77704268 hasConceptScore W77704268C108650721 @default.
- W77704268 hasConceptScore W77704268C111472728 @default.
- W77704268 hasConceptScore W77704268C119857082 @default.
- W77704268 hasConceptScore W77704268C124304363 @default.
- W77704268 hasConceptScore W77704268C138885662 @default.
- W77704268 hasConceptScore W77704268C144237770 @default.
- W77704268 hasConceptScore W77704268C15744967 @default.
- W77704268 hasConceptScore W77704268C165064840 @default.
- W77704268 hasConceptScore W77704268C33923547 @default.
- W77704268 hasConceptScore W77704268C41008148 @default.
- W77704268 hasConceptScore W77704268C42475967 @default.
- W77704268 hasConceptScore W77704268C50817715 @default.
- W77704268 hasConceptScore W77704268C77805123 @default.
- W77704268 hasLocation W777042681 @default.
- W77704268 hasOpenAccess W77704268 @default.
- W77704268 hasPrimaryLocation W777042681 @default.
- W77704268 hasRelatedWork W1192553058 @default.
- W77704268 hasRelatedWork W1542941925 @default.
- W77704268 hasRelatedWork W1607392272 @default.
- W77704268 hasRelatedWork W190498140 @default.
- W77704268 hasRelatedWork W1973039793 @default.
- W77704268 hasRelatedWork W2067050450 @default.
- W77704268 hasRelatedWork W2096145798 @default.
- W77704268 hasRelatedWork W2103315867 @default.
- W77704268 hasRelatedWork W2119717200 @default.
- W77704268 hasRelatedWork W2120846115 @default.
- W77704268 hasRelatedWork W2121863487 @default.
- W77704268 hasRelatedWork W2126316555 @default.
- W77704268 hasRelatedWork W2144274908 @default.
- W77704268 hasRelatedWork W2145943204 @default.
- W77704268 hasRelatedWork W2152897361 @default.
- W77704268 hasRelatedWork W2156060009 @default.
- W77704268 hasRelatedWork W2257979135 @default.
- W77704268 hasRelatedWork W2736601468 @default.
- W77704268 hasRelatedWork W2766447205 @default.
- W77704268 hasRelatedWork W2773381986 @default.
- W77704268 isParatext "false" @default.
- W77704268 isRetracted "false" @default.
- W77704268 magId "77704268" @default.
- W77704268 workType "article" @default.