On the utility of dreaming: a general model for how learning in artificial agents can benefit from data hallucination
Article
Windridge, D., Svensson, H. and Thill, S. 2021. On the utility of dreaming: a general model for how learning in artificial agents can benefit from data hallucination. Adaptive Behavior. 29 (3), pp. 267-280. https://doi.org/10.1177/1059712319896489
Type | Article |
---|---|
Title | On the utility of dreaming: a general model for how learning in artificial agents can benefit from data hallucination |
Authors | Windridge, D., Svensson, H. and Thill, S. |
Abstract | We consider the benefits of dream mechanisms – that is, the ability to simulate new experiences based on past ones – in a machine learning context. Specifically, we are interested in learning for artificial agents that act in the world, and operationalize “dreaming” as a mechanism by which such an agent can use its own model of the learning environment to generate new hypotheses and training data. |
Keywords | Artificial dream mechanisms; data simulation; machine learning; reinforcement learning |
Publisher | SAGE Publications |
Journal | Adaptive Behavior |
ISSN | 1059-7123 |
Electronic | 1741-2633 |
Publication dates | |
Online | 08 Jan 2020 |
01 Jun 2021 | |
Publication process dates | |
Deposited | 15 Jan 2020 |
Accepted | 01 Jan 2020 |
Output status | Published |
Publisher's version | License |
Copyright Statement | Copyright © The Author(s) 2020. |
Digital Object Identifier (DOI) | https://doi.org/10.1177/1059712319896489 |
Web of Science identifier | WOS:000506780000001 |
Language | English |
https://repository.mdx.ac.uk/item/88vv0
Download files
64
total views13
total downloads4
views this month1
downloads this month