Documents disponibles écrits par cet auteur

Comparing reinforcement learning approaches for solving game theoretic models / A. Collins in Journal of the operational research society (JORS), Vol. 63 N° 8 (Août 2012) 

Public ISBD [article]  in Journal of the operational research society (JORS) > Vol. 63 N° 8 (Août 2012) . - pp. 1165–1173 Titre : Comparing reinforcement learning approaches for solving game theoretic models : a dynamic airline pricing game example Type de document : texte imprimé Auteurs : A. Collins, Auteur ; L. Thomas, Auteur Année de publication : 2012 Article en page(s) : pp. 1165–1173 Note générale : Operational research Langues : Anglais (eng) Mots-clés : Game  theory  Artificial  intelligence  Reinforcement  learning  Air  transport Index. décimale : 001.424 Résumé : Games can be easy to construct but difficult to solve due to current methods available for finding the Nash Equilibrium. This issue is one of many that face modern game theorists and those analysts that need to model situations with multiple decision-makers. This paper explores the use of reinforcement learning, a standard artificial intelligence technique, as a means to solve a simple dynamic airline pricing game. Three different reinforcement learning approaches are compared: SARSA, Q-learning and Monte Carlo Learning. The pricing game solution is surprisingly sophisticated given the game's simplicity and this sophistication is reflected in the learning results. The paper also discusses extra analytical benefit obtained from applying reinforcement learning to these types of problems. DEWEY : 001.424 ISSN : 0160-5682 En ligne : http://www.palgrave-journals.com/jors/journal/v63/n8/abs/jors201194a.html [article] Comparing reinforcement learning approaches for solving game theoretic models : a dynamic airline pricing game example [texte imprimé] / A. Collins, Auteur ; L. Thomas, Auteur . - 2012 . - pp. 1165–1173. Operational research Langues : Anglais (eng) in Journal of the operational research society (JORS) > Vol. 63 N° 8 (Août 2012) . - pp. 1165–1173 Mots-clés : Game  theory  Artificial  intelligence  Reinforcement  learning  Air  transport Index. décimale : 001.424 Résumé : Games can be easy to construct but difficult to solve due to current methods available for finding the Nash Equilibrium. This issue is one of many that face modern game theorists and those analysts that need to model situations with multiple decision-makers. This paper explores the use of reinforcement learning, a standard artificial intelligence technique, as a means to solve a simple dynamic airline pricing game. Three different reinforcement learning approaches are compared: SARSA, Q-learning and Monte Carlo Learning. The pricing game solution is surprisingly sophisticated given the game's simplicity and this sophistication is reflected in the learning results. The paper also discusses extra analytical benefit obtained from applying reinforcement learning to these types of problems. DEWEY : 001.424 ISSN : 0160-5682 En ligne : http://www.palgrave-journals.com/jors/journal/v63/n8/abs/jors201194a.html