[Home]   [  News]   [  Events]   [  People]   [  Research]   [  Education]   [Visitor Info]   [UCSD Only]   [Admin]
Home > Events > CCoM > Abstract
Search this site:

Higher Order Methods for Bayesian Bandits

Nicholas Zhao


Bayesian Optimal policy with large horizon can be approximated by HJB equation. ENO in state space and RK in time are used to strive for higher order convergence to the Regularized and Unregularized version of HJB equation. Convergence analysis, possible sharper bound for CFL condition, and performance of adaptive time-stepping are also studied.

Tuesday, April 16, 2024
11:00AM AP&M 2402 and Zoom ID 982 8500 1195