TurKPF: TurKontrol as a Particle Filter

TL;DR

TurKPF re-implements the TurKontrol algorithm using a particle filter to enhance computational efficiency, achieving near-instantaneous action selection while maintaining similar performance levels.

Contribution

This paper introduces TurKPF, a particle filter-based version of TurKontrol, reducing computation time and memory usage in crowdsourced workflow control.

Findings

TurKPF performs similarly to TurKontrol in experiments.

TurKPF achieves near-instantaneous action selection.

Uses less memory and computation time.

Abstract

TurKontrol, and algorithm presented in (Dai et al. 2010), uses a POMDP to model and control an iterative workflow for crowdsourced work. Here, TurKontrol is re-implemented as "TurKPF," which uses a Particle Filter to reduce computation time & memory usage. Most importantly, in our experimental environment with default parameter settings, the action is chosen nearly instantaneously. Through a series of experiments we see that TurKPF and TurKontrol perform similarly.