Modeling Goal Selection with Program Synthesis
Abstract
People can autonomously select and achieve novel goals to shape their own learning. But goal selection can involve selecting goals from large spaces, where repeated planning becomes computationally intractable. We propose program induction as an inductive bias for defining human-like priors to make goal selection easier. We demonstrate this tractable, semi-autonomous method for goal selection on a novel ShapeWorld task using a handcrafted grammar that maps states to reward functions.
Cite
Text
Byers et al. "Modeling Goal Selection with Program Synthesis." NeurIPS 2024 Workshops: IMOL, 2024.Markdown
[Byers et al. "Modeling Goal Selection with Program Synthesis." NeurIPS 2024 Workshops: IMOL, 2024.](https://mlanthology.org/neuripsw/2024/byers2024neuripsw-modeling/)BibTeX
@inproceedings{byers2024neuripsw-modeling,
title = {{Modeling Goal Selection with Program Synthesis}},
author = {Byers, J. Branson and Zhao, Bonan and Niv, Yael},
booktitle = {NeurIPS 2024 Workshops: IMOL},
year = {2024},
url = {https://mlanthology.org/neuripsw/2024/byers2024neuripsw-modeling/}
}