Regret bounds for Gaussian process bandits without observation noise
This thesis presents some statistical refinements of the bandits approach presented in [11] in the situation where there is no observation noise. We give an improved bound on the cumulative regret of the samples chosen by an algorithm that is related (though not identical) to the UCB algorithm of [1...
| Main Author: | |
|---|---|
| Language: | English |
| Published: |
University of British Columbia
2012
|
| Online Access: | http://hdl.handle.net/2429/42865 |