Causal Campbell-Goodhart’s Law and Reinforcement Learning

Hal Ashton

2021

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.

Paper Citation

in Harvard Style

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, ISBN 978-989-758-484-8, pages 67-73. DOI: 10.5220/0010197300670073

in Bibtex Style

@conference{icaart21,
author={Hal Ashton},
title={Causal Campbell-Goodhart’s Law and Reinforcement Learning},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2021},
pages={67-73},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010197300670073},
isbn={978-989-758-484-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Causal Campbell-Goodhart’s Law and Reinforcement Learning
SN - 978-989-758-484-8
AU - Ashton H.
PY - 2021
SP - 67
EP - 73
DO - 10.5220/0010197300670073