Interactive Reinforcement Learning for Symbolic Regression from Multi-Format Human-Preference Feedbacks
Abstract
In this work, we propose an interactive platform to perform grammar-guided symbolic regression using a reinforcement learning approach from human-preference feedback. To do so, a reinforcement learning algorithm iteratively generates symbolic expressions, modeled as trajectories constrained by grammatical rules, from which a user shall elicit preferences. The interface gives the user three distinct ways of stating its preferences between multiple sampled symbolic expressions: categorizing samples, comparing pairs, and suggesting improvements to a sampled symbolic expression. Learning from preferences enables users to guide the exploration in the symbolic space toward regions that are more relevant to them. We provide a web-based interface testable on symbolic regression benchmark functions and power system data.
Cite
Text
Crochepierre et al. "Interactive Reinforcement Learning for Symbolic Regression from Multi-Format Human-Preference Feedbacks." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/849Markdown
[Crochepierre et al. "Interactive Reinforcement Learning for Symbolic Regression from Multi-Format Human-Preference Feedbacks." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/crochepierre2022ijcai-interactive/) doi:10.24963/IJCAI.2022/849BibTeX
@inproceedings{crochepierre2022ijcai-interactive,
title = {{Interactive Reinforcement Learning for Symbolic Regression from Multi-Format Human-Preference Feedbacks}},
author = {Crochepierre, Laure and Boudjeloud-Assala, Lydia and Barbesant, Vincent},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2022},
pages = {5900-5903},
doi = {10.24963/IJCAI.2022/849},
url = {https://mlanthology.org/ijcai/2022/crochepierre2022ijcai-interactive/}
}