Probabilistic Loss and its Online Characterization for Simplified Decision Making Under Uncertainty

TL;DR

This paper introduces a comprehensive framework for decision making under uncertainty that quantifies and controls the impact of simplifications, improving reliability and efficiency in complex stochastic scenarios.

Contribution

It extends decision making mechanisms by removing standard approximations, introduces a novel framework for online simplification assessment, and provides stochastic bounds on returns.

Findings

Effective online assessment of simplification impact

Stochastic bounds improve decision reliability

Simulation results demonstrate approach advantages

Abstract

It is a long-standing objective to ease the computation burden incurred by the decision making process. Identification of this mechanism's sensitivity to simplification has tremendous ramifications. Yet, algorithms for decision making under uncertainty usually lean on approximations or heuristics without quantifying their effect. Therefore, challenging scenarios could severely impair the performance of such methods. In this paper, we extend the decision making mechanism to the whole by removing standard approximations and considering all previously suppressed stochastic sources of variability. On top of this extension, our key contribution is a novel framework to simplify decision making while assessing and controlling online the simplification's impact. Furthermore, we present novel stochastic bounds on the return and characterize online the effect of simplification using this framework on a particular simplification technique - reducing the number of samples in belief representation for planning. Finally, we verify the advantages of our approach through extensive simulations.