Accession Number : AD1045845

Title :   Adaptive Decision Making Using Probabilistic Programming and Stochastic Optimization

Descriptive Note : Technical Report,01 Nov 2016,01 Aug 2017

Corporate Author : Carnegie Mellon University Pittsburgh United States

Personal Author(s) : Kolter,J Z

Full Text :

Report Date : 01 Jan 2018

Pagination or Media Count : 35

Abstract : This work seeks to understand the connections between learning and decision making under uncertainty. Specifically, we ask that question: when we are going to use learned models within the loop of a larger decision making process, how should we alter the learning procedure or somehow tune the learning to the specific needs of the actual decision making task? To answer this question, we developed a theory of task based model learning, learning models tuned not (just) for predictive accuracy, but to optimize the closed loop performance of a decision making procedure (specifically, those based on stochastic optimization) that uses these models as an intermediate step. Training such models requires that we differentiate through an optimization problem, for which we developed the theory and implementations. On several tasks, we show that such learning substantially outperforms traditional learning processes, where the learning and decision making stages are separate.

Descriptors :   learning machines , optimization , Stochastic processes , DECISION MAKING , PROBABILITY

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE