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

Identifiability of Gaussian Bayesian bandit models

Speekenbrink, M; (2019) Identifiability of Gaussian Bayesian bandit models. In: Proceedings of the 2019 Conference on Cognitive Computational Neuroscience. (pp. pp. 686-688). Cognitive Computational Neuroscience: Berlin, Germany. Green open access

[thumbnail of 0000686.pdf]
Preview
Text
0000686.pdf - Published Version

Download (161kB) | Preview

Abstract

The Kalman filter, combined with heuristic choice rules such as softmax, UCB, and Thompson sampling, has been a popular model to identify the role of uncertainty in exploration in human reinforcement learning. Here we show that the Kalman filter combined with a softmax or UCB choice rule is not fully identifiable. By this structural identifiability, we mean that with unlimited data, the true parameter values are determinable. Perhaps surprisingly, the Kalman filter with Thompson sampling is fully identifiable.

Type: Proceedings paper
Title: Identifiability of Gaussian Bayesian bandit models
Event: 2019 Conference on Cognitive Computational Neuroscience
Dates: 13 September 2019 - 16 September 2019
Open access status: An open access version is available from UCL Discovery
DOI: 10.32470/ccn.2019.1335-0
Publisher version: https://doi.org/10.32470/CCN.2019.1335-0
Language: English
Additional information: This work is licensed under the Creative Commons Attribution 3.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/3.0
Keywords: Identifiability; Kalman filter; Softmax; UCB; Thompson sampling; Multi-Armed Bandits
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
URI: https://discovery.ucl.ac.uk/id/eprint/10138392
Downloads since deposit
113Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item