Modeling Strategies as Programs: How to Study Strategy Differences in Intelligent Systems with Program Synthesis
Abstract
When faced with novel tasks, humans have the ability to form successful strategies, seemingly without much effort. Artificial systems, on the other, hand cannot, at least when the flexibility at which humans perform is considered. For my dissertation, I am using program synthesis as a tool to study the factors that affect strategy choices in intelligent systems. I am evaluating my work through agents that reason through problems from the Abstract Reasoning Corpus and The Block Design Task.
Cite
Text
Ainooson. "Modeling Strategies as Programs: How to Study Strategy Differences in Intelligent Systems with Program Synthesis." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.26915Markdown
[Ainooson. "Modeling Strategies as Programs: How to Study Strategy Differences in Intelligent Systems with Program Synthesis." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/ainooson2023aaai-modeling/) doi:10.1609/AAAI.V37I13.26915BibTeX
@inproceedings{ainooson2023aaai-modeling,
title = {{Modeling Strategies as Programs: How to Study Strategy Differences in Intelligent Systems with Program Synthesis}},
author = {Ainooson, James},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2023},
pages = {16109-16110},
doi = {10.1609/AAAI.V37I13.26915},
url = {https://mlanthology.org/aaai/2023/ainooson2023aaai-modeling/}
}