A modern Bayesian look at the multiarmed bandit

First Page		Document Content
Date: 2011-03-31 14:42:20 Machine learning Multi-armed bandit Stochastic optimization Decision theory Gittins index Reinforcement learning Bandit Kullback–Leibler divergence Probability distribution Statistics Design of experiments Statistical theory		A modern Bayesian look at the multiarmed bandit Add to Reading List Source URL: www.economics.uci.edu Download Document from Source Website File Size: 791,23 KB Share Document on Facebook

	Online Learning for Personalized Room-Level Thermal Control: A Multi-Armed Bandit Framework Parisa Mansourifard Farrokh Jazizadeh DocID: 1vhJI - View Document
	Supplementary Material for ”Combinatorial multi-armed bandit: general framework, results and applications”, by Wei Chen, Yajun Wang, and Yang Yuan. A. Full proof of Theorem 1 We use the following two well known bound DocID: 1v3uQ - View Document
	Combinatorial Multi-Armed Bandit: General Framework, Results and Applications Wei Chen Microsoft Research Asia, Beijing, China DocID: 1uuiO - View Document
	THE NON-BAYESIAN RESTLESS MULTI-ARMED BANDIT: A CASE OF NEAR-LOGARITHMIC REGRET Wenhan Dai†∗ , Yi Gai‡ , Bhaskar Krishnamachari‡ , Qing Zhao§ † School of Information Science and Technology, Tsinghua Universit DocID: 1uswd - View Document
	Online Algorithms for the Multi-Armed Bandit Problem with Markovian Rewards arXiv:1007.2238v2 [math.OC] 26 JulCem Tekin, Mingyan Liu DocID: 1u0WJ - View Document