Multi-armed bandit - PDFSEARCH.IO - Document Search Engine

Multi-armed bandit
Results: 113

#	Item
41	Almost Optimal Exploration in Multi-Armed Bandits Zohar Karnin Yahoo! Labs, Haifa, Israel Tomer Koren† Technion—Israel Institute of Technology, Haifa, Israel Add to Reading List Source URL: jmlr.org Language: English - Date: 2013-08-14 01:36:43 Mathematics Computational complexity theory Mathematical analysis Machine learning Multi-armed bandit Stochastic optimization Algorithm Exponential time hypothesis Big O notation
42	Nearly Tight Bounds for the Continuum-Armed Bandit Problem Robert Kleinberg∗ Abstract In the multi-armed bandit problem, an online algorithm must choose Add to Reading List Source URL: papers.nips.cc Language: English - Date: 2013-11-28 03:24:53
43	JMLR: Workshop and Conference Proceedings vol–36 On-line Trading of Exploration and Exploitation 2 An Unbiased Offline Evaluation of Contextual Bandit Algorithms with Generalized Linear Models Add to Reading List Source URL: jmlr.org Language: English - Date: 2012-05-02 03:57:00 Machine learning Artificial intelligence Learning Cognition Markov models Multi-armed bandit Stochastic optimization Reinforcement learning Algorithm Stability Recommender system Greedy algorithm
44	Journal of Machine Learning Research Submitted 1/04; Published 6/04 The Sample Complexity of Exploration in the Multi-Armed Bandit Problem Add to Reading List Source URL: www.jmlr.org Language: English - Date: 2004-08-31 14:12:33
45	M ULTI –A RMED BANDIT FOR P RICING Multi–Armed Bandit for Pricing Francesco Trov`o FRANCESCO 1. TROVO @ POLIMI . IT Add to Reading List Source URL: ewrl.files.wordpress.com Language: English - Date: 2015-06-22 05:16:23
46	Automatic Ad Format Selection via Contextual Bandits Liang Tang School of Computer Science Florida International UnivS.W. 8th St. Add to Reading List Source URL: people.csail.mit.edu Language: English - Date: 2013-09-28 16:14:54 Reinforcement learning Greedy algorithm Multi-armed bandit Search advertising Prime-counting function Online advertising Statistics Mathematics Mathematical analysis
47	BANDITS WITHOUT REGRETS: THE POWER OF ADAPTIVE ADVERSARIES Nicol`o Cesa-Bianchi Dipartimento di Informatica Universit`a degli Studi di Milano, Italy Add to Reading List Source URL: www.me.inf.kyushu-u.ac.jp Language: English - Date: 2013-10-14 22:31:27 Online algorithms Adversary model Adversary Multi-armed bandit Regret Switching barriers Bandit Costs Bianchi Statistics Decision theory Analysis of algorithms
48	Resource-Sharing in a Single Server with Time-Varying Capacity (Invited Paper) Urtzi Ayesta∗† , Martin Erausquin∗‡ , Peter Jacko∗ ∗ BCAM—Basque Add to Reading List Source URL: homepages.laas.fr Language: English - Date: 2012-01-01 05:04:48 Gittins index Multi-armed bandit Digital signal processing Statistics Decision theory Design of experiments
49	Stochastic and fluid index policies for resource allocation problems M. Larran˜aga1,2,5 , U. Ayesta2,3,4,5 , I.M. Verloop1,5 IRIT, 2 rue C. Carmichel, FToulouse, France. 2 CNRS, LAAS, 7 avenue du colonel Roche, F Add to Reading List Source URL: verloop.perso.enseeiht.fr Language: English - Date: 2015-04-01 14:42:52 Systems theory Dynamic programming Operations research Equations Optimal control Bellman equation Multi-armed bandit Markov decision process Relaxation Statistics Mathematical optimization Control theory
50	Stochastic and fluid index policies for resource allocation problems M. Larran˜aga1,2,5 , U. Ayesta2,3,4,5 , I.M. Verloop1,5 IRIT, 2 rue C. Carmichel, FToulouse, France. 2 CNRS, LAAS, 7 avenue du colonel Roche, F Add to Reading List Source URL: homepages.laas.fr Language: English - Date: 2015-02-17 15:01:29 Systems theory Dynamic programming Operations research Equations Optimal control Bellman equation Multi-armed bandit Markov decision process Relaxation Statistics Mathematical optimization Control theory