Technical Talk: Active Hypothesis Testing: Musings on the non-Asymptotic Case

Bush House Room (SE)1.01, Bush House, King's College, 30 Aldwych, London

As part of this technical talk, the speaker explores neural network implementations to solve the Markov Decision Process problem (MDP) and show that success is strongly tied to the particular implementation and the design of the right metric as informed by our analytical work. Our infinite horizon solutions are shown to outperform recent strategies in the finite horizon case. We make connections to key information theoretic quantities that have been previously considered and provide numerical results.

Go to Top