Matches in SemOpenAlex for { <https://semopenalex.org/work/W2920763178> ?p ?o ?g. }
- W2920763178 abstract "Counterfactual Regret Minimization (CFR) has found success in settings like poker which have both terminal states and perfect recall. We seek to understand how to relax these requirements. As a first step, we introduce a simple algorithm, local no-regret learning (LONR), which uses a Q-learning-like update rule to allow learning without terminal states or perfect recall. We prove its convergence for the basic case of MDPs (and limited extensions of them) and present empirical results showing that it achieves last iterate convergence in a number of settings, most notably NoSDE games, a class of Markov games specifically designed to be challenging to learn where no prior algorithm is known to achieve convergence to a stationary equilibrium even on average." @default.
- W2920763178 created "2019-03-11" @default.
- W2920763178 creator A5027441885 @default.
- W2920763178 creator A5045648666 @default.
- W2920763178 creator A5072210522 @default.
- W2920763178 date "2019-10-07" @default.
- W2920763178 modified "2023-09-27" @default.
- W2920763178 title "Combining No-regret and Q-learning" @default.
- W2920763178 cites W1486300442 @default.
- W2920763178 cites W1525285119 @default.
- W2920763178 cites W1531245405 @default.
- W2920763178 cites W1542941925 @default.
- W2920763178 cites W1579312135 @default.
- W2920763178 cites W1726776292 @default.
- W2920763178 cites W1826788 @default.
- W2920763178 cites W1861050369 @default.
- W2920763178 cites W2006791053 @default.
- W2920763178 cites W2074680702 @default.
- W2920763178 cites W2077902449 @default.
- W2920763178 cites W2100752967 @default.
- W2920763178 cites W2102509082 @default.
- W2920763178 cites W2103315867 @default.
- W2920763178 cites W2106975967 @default.
- W2920763178 cites W2119380668 @default.
- W2920763178 cites W2120846115 @default.
- W2920763178 cites W2122187689 @default.
- W2920763178 cites W2122701159 @default.
- W2920763178 cites W2126776273 @default.
- W2920763178 cites W2127974068 @default.
- W2920763178 cites W2135829225 @default.
- W2920763178 cites W2145943204 @default.
- W2920763178 cites W2154806059 @default.
- W2920763178 cites W2156211713 @default.
- W2920763178 cites W2164637474 @default.
- W2920763178 cites W2248846161 @default.
- W2920763178 cites W2275626685 @default.
- W2920763178 cites W2276878381 @default.
- W2920763178 cites W2286652700 @default.
- W2920763178 cites W2291986326 @default.
- W2920763178 cites W2574978968 @default.
- W2920763178 cites W2619268125 @default.
- W2920763178 cites W2765094320 @default.
- W2920763178 cites W2766768413 @default.
- W2920763178 cites W2811481615 @default.
- W2920763178 cites W2863175877 @default.
- W2920763178 cites W2892013712 @default.
- W2920763178 cites W2899081098 @default.
- W2920763178 cites W2899851451 @default.
- W2920763178 cites W2906281181 @default.
- W2920763178 cites W2914115734 @default.
- W2920763178 cites W2914411420 @default.
- W2920763178 cites W2914476425 @default.
- W2920763178 cites W2945065307 @default.
- W2920763178 cites W2948127421 @default.
- W2920763178 cites W2950376443 @default.
- W2920763178 cites W2960876848 @default.
- W2920763178 cites W2962173422 @default.
- W2920763178 cites W2962847657 @default.
- W2920763178 cites W2963754245 @default.
- W2920763178 cites W2964067523 @default.
- W2920763178 cites W2966397236 @default.
- W2920763178 hasPublicationYear "2019" @default.
- W2920763178 type Work @default.
- W2920763178 sameAs 2920763178 @default.
- W2920763178 citedByCount "2" @default.
- W2920763178 countsByYear W29207631782018 @default.
- W2920763178 countsByYear W29207631782020 @default.
- W2920763178 crossrefType "posted-content" @default.
- W2920763178 hasAuthorship W2920763178A5027441885 @default.
- W2920763178 hasAuthorship W2920763178A5045648666 @default.
- W2920763178 hasAuthorship W2920763178A5072210522 @default.
- W2920763178 hasConcept C100660578 @default.
- W2920763178 hasConcept C105795698 @default.
- W2920763178 hasConcept C106189395 @default.
- W2920763178 hasConcept C108650721 @default.
- W2920763178 hasConcept C111472728 @default.
- W2920763178 hasConcept C119857082 @default.
- W2920763178 hasConcept C126255220 @default.
- W2920763178 hasConcept C127705205 @default.
- W2920763178 hasConcept C138885662 @default.
- W2920763178 hasConcept C144237770 @default.
- W2920763178 hasConcept C154945302 @default.
- W2920763178 hasConcept C15744967 @default.
- W2920763178 hasConcept C159886148 @default.
- W2920763178 hasConcept C162324750 @default.
- W2920763178 hasConcept C173801870 @default.
- W2920763178 hasConcept C180747234 @default.
- W2920763178 hasConcept C188116033 @default.
- W2920763178 hasConcept C2777212361 @default.
- W2920763178 hasConcept C2777303404 @default.
- W2920763178 hasConcept C2779664074 @default.
- W2920763178 hasConcept C2780586882 @default.
- W2920763178 hasConcept C33923547 @default.
- W2920763178 hasConcept C41008148 @default.
- W2920763178 hasConcept C50522688 @default.
- W2920763178 hasConcept C50817715 @default.
- W2920763178 hasConcept C76155785 @default.
- W2920763178 hasConcept C77805123 @default.
- W2920763178 hasConcept C97541855 @default.
- W2920763178 hasConcept C98763669 @default.