Thompson Sampling for Complex Online Problems

First Page		Document Content
Date: 2014-02-16 19:30:21 Econometrics Statistical inference Machine learning Confidence interval Multi-armed bandit Thompson sampling Reinforcement learning Bayes estimator Dimensional analysis Statistics Measurement Estimation theory		Thompson Sampling for Complex Online Problems Add to Reading List Source URL: jmlr.org Download Document from Source Website File Size: 3,17 MB Share Document on Facebook

	Journal of Machine Learning Research 1 (year) pages Submitted 4/00; PublishedLinear Thompson Sampling Revisited Marc Abeille DocID: 1tpbJ - View Document
	Clearwater River Habitat/Bioassessment Project #46K Sampling and Analysis Plan The Red Lake Watershed District Index of BioIntegrity for the Clearwater River Habitat and Bioassessment Project #46K DocID: 1rmgD - View Document
	JMLR: Workshop and Conference Proceedings vol 40:1–38, 2015 Thompson Sampling for Learning Parameterized Markov Decision Processes Aditya Gopalan DocID: 1qpMW - View Document
	JMLR: Workshop and Conference Proceedings vol–25th Annual Conference on Learning Theory Analysis of Thompson Sampling for the Multi-armed Bandit Problem Shipra Agrawal DocID: 1nFsD - View Document
	Further Optimal Regret Bounds for Thompson Sampling Navin Goyal Microsoft Research India arXiv:1209.3353v1 [cs.LG] 15 Sep 2012 DocID: 1mquD - View Document