Adaptive Decision Making Using Probabilistic Programming and Stochastic Optimization
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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2018
- Accession Number
- AD1045845
Entities
People
- J. Z. Kolter
Organizations
- Carnegie Mellon University