UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Better safe than sorry: Risky function exploitation through safe optimization

Schulz, E; Huys, QJM; Bach, DR; Speekenbrink, M; Krause, A; (2016) Better safe than sorry: Risky function exploitation through safe optimization. In: Proceedings of the 38th Annual Meeting of the Cognitive Science Society. (pp. pp. 1140-1145). Cognitive Science Society: Austin, TX. Green open access

[thumbnail of paper0205.pdf] Text
paper0205.pdf - Published Version
Available under License : See the attached licence file.

Download (628kB)

Abstract

Exploration-exploitation of functions, that is learning and optimizing a mapping between inputs and expected outputs, is ubiquitous to many real world situations. These situations sometimes require us to avoid certain outcomes at all cost, for example because they are poisonous, harmful, or otherwise dangerous. We test participants' behavior in scenarios in which they have to find the optimum of a function while at the same time avoid outputs below a certain threshold. In two experiments, we find that Safe-Optimization, a Gaussian Process-based exploration-exploitation algorithm, describes participants' behavior well and that participants seem to care firstly whether a point is safe and then try to pick the optimal point from all such safe points. This means that their trade-off between exploration and exploitation can be seen as an intelligent, approximate, and homeostasis-driven strategy.

Type: Proceedings paper
Title: Better safe than sorry: Risky function exploitation through safe optimization
Event: 38th Annual Conference of the Cognitive Science Society
Location: Austin, TX
ISBN-13: 9780991196739
Open access status: An open access version is available from UCL Discovery
Publisher version: https://mindmodeling.org/cogsci2016/papers/0205/in...
Language: English
Additional information: Copyright © The Authors 2016.
Keywords: Safe Optimization, Function Learning, Approximate Learning, Gaussian Process, Homeostasis
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > Div of Psychology and Lang Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > Div of Psychology and Lang Sciences > Experimental Psychology
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > Division of Psychiatry
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > UCL Queen Square Institute of Neurology
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > UCL Queen Square Institute of Neurology > Imaging Neuroscience
URI: https://discovery.ucl.ac.uk/id/eprint/1493693
Downloads since deposit
30Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item