2026-09-21T05:00:42Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/18352 2023-07-10 col_2142_5131 com_2142_5130

machine learning Parametrized Stochastic Multi-armed Bandits with Binary Rewards Srikant, Rayadurgam Jiang, Chong 2011-01-14T22:47:13Z 2011-01-14T22:47:13Z 2011-01-14T22:47:13Z In this thesis, we consider the problem of multi-armed bandits with a large number of correlated arms. We assume that the arms have Bernoulli distributed rewards, independent across arms and across time, where the probabilities of success are parametrized by known attribute vectors for each arm, as well as an unknown preference vector. For this model, we seek an algorithm with a total regret that is sub-linear in time and independent of the number of arms. We present such an algorithm, which we call the Three-phase Algorithm, and analyze its performance. We show an upper bound on the total regret which applies uniformly in time. The asymptotics of this bound show that for any $f \in \omega(\log(T))$, the total regret can be made to be $O(f(T))$, independent of the number of arms. Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2010-12-09T18:39:12Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Jiang_Chong.pdf: 325450 bytes, checksum: 9f6372630df4d279f19fca565c89d472 (MD5) Made available in DSpace on 2011-01-14T22:47:13Z (GMT). No. of bitstreams: 2 Jiang_Chong.pdf: 325450 bytes, checksum: 9f6372630df4d279f19fca565c89d472 (MD5) license.txt: 4060 bytes, checksum: 9148706d902e93953c049052831ab198 (MD5) http://hdl.handle.net/2142/18352 en Copyright 2010 Chong Jiang multi-armed bandits 2010-12 Electrical & Computer Eng 1933 Electrical & Computer Engr 1200 University of Illinois at Urbana-Champaign Thesis M.S. PHD:Electr & Computer Eng-UIUC 10KS1200PHD