Ashton, H;
(2021)
Causal Campbell-Goodhart’s Law and Reinforcement Learning.
In:
Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART.
(pp. pp. 67-73).
SciTePress, Science and Technology Publications
Preview |
Text
Dog_Barometer_submission_ICAART(4).pdf - Accepted Version Download (184kB) | Preview |
Abstract
Campbell-Goodhart’s law relates to the causal inference error whereby decision-making agents aim to influence variables which are correlated to their goal objective but do not reliably cause it. This is a well known error in Economics and Political Science but not widely labelled in Artificial Intelligence research. Through a simple example, we show how off-the-shelf deep Reinforcement Learning (RL) algorithms are not necessarily immune to this cognitive error. The off-policy learning method is tricked, whilst the on-policy method is not. The practical implication is that naive application of RL to complex real life problems can result in the same types of policy errors that humans make. Great care should be taken around understanding the causal model that underpins a solution derived from Reinforcement Learning.
| Type: | Proceedings paper |
|---|---|
| Title: | Causal Campbell-Goodhart’s Law and Reinforcement Learning |
| Event: | 13th International Conference on Agents and Artificial Intelligence |
| ISBN-13: | 978-989-758-484-8 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.5220/0010197300670073 |
| Publisher version: | https://doi.org/10.5220/0010197300670073 |
| Language: | English |
| Additional information: | © 2021 SciTePress, Science and Technology Publications. This is an Open Access publication distributed under the terms of a Creative Commons licence (https://creativecommons.org/licenses/by-nc-nd/4.0/). |
| Keywords: | Reinforcement Learning, Goodhart’s Law, Campbell’s Law, Causal Inference, Cognitive Error |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10117316 |
Archive Staff Only
 |
View Item |
