The Library
From eye-blinks to state construction : diagnostic benchmarks for online representation learning
Tools
Tools
Tools
Rafiee, Banafsheh, Abbas, Zaheer, Ghiassian, Sina, Kumaraswamy, Raksha, Sutton, Richard S., Ludvig, Elliot Andrew and White, Adam (2023) From eye-blinks to state construction : diagnostic benchmarks for online representation learning. Adaptive Behavior, 31 (1). pp. 3-19. doi:10.1177/10597123221085039 ISSN 1059-7123.
|
PDF
WRAP-from-eye-blinks-state-construction-diagnostic-benchmarks-online-representation-learning-Ludvig-2022.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (2018Kb) | Preview |
|
![[img]](https://wrap.warwick.ac.uk/style/images/fileicons/application_pdf.png) |
PDF
WRAP-from-eye-blinks-state-construction-diagnostic-benchmarks-online-representation-learning-Ludvig-2022.pdf - Accepted Version Embargoed item. Restricted access to Repository staff only - Requires a PDF viewer. Download (8Mb) |
Official URL: https://doi.org/10.1177/10597123221085039
Abstract
We present three new diagnostic prediction problems inspired by classical-conditioning experiments to facilitate research in online prediction learning. Experiments in classical conditioning show that animals such as rabbits, pigeons, and dogs can make long temporal associations that enable multi-step prediction. To replicate this remarkable ability, an agent must construct an internal state representation that summarizes its interaction history. Recurrent neural networks can automatically construct state and learn temporal associations. However, the current training methods are prohibitively expensive for online prediction—continual learning on every time step—which is the focus of this paper. Our proposed problems test the learning capabilities that animals readily exhibit and highlight the limitations of the current recurrent learning methods. While the proposed problems are nontrivial, they are still amenable to extensive testing and analysis in the small-compute regime, thereby enabling researchers to study issues in isolation, ultimately accelerating progress towards scalable online representation learning method.
| Item Type: | Journal Article | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Alternative Title: | |||||||||||||||||||
| Subjects: | B Philosophy. Psychology. Religion > BF Psychology L Education > LB Theory and practice of education Q Science > Q Science (General) |
||||||||||||||||||
| Divisions: | Faculty of Science, Engineering and Medicine > Science > Psychology | ||||||||||||||||||
| Library of Congress Subject Headings (LCSH): | Reinforcement learning, Machine learning, Artificial intelligence -- Educational applications, Cognitive science, Learning, Psychology of | ||||||||||||||||||
| Journal or Publication Title: | Adaptive Behavior | ||||||||||||||||||
| Publisher: | SAGE Publications | ||||||||||||||||||
| ISSN: | 1059-7123 | ||||||||||||||||||
| Official Date: | February 2023 | ||||||||||||||||||
| Dates: |
|
||||||||||||||||||
| Volume: | 31 | ||||||||||||||||||
| Number: | 1 | ||||||||||||||||||
| Page Range: | pp. 3-19 | ||||||||||||||||||
| DOI: | 10.1177/10597123221085039 | ||||||||||||||||||
| Status: | Peer Reviewed | ||||||||||||||||||
| Publication Status: | Published | ||||||||||||||||||
| Access rights to Published version: | Open Access (Creative Commons) | ||||||||||||||||||
| Date of first compliant deposit: | 16 February 2022 | ||||||||||||||||||
| Date of first compliant Open Access: | 21 February 2022 | ||||||||||||||||||
| RIOXX Funder/Project Grant: |
|
||||||||||||||||||
| Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
Downloads
Downloads per month over past year
