In the task of automatic program synthesis, one obtains pairs of matching inputs and outputs and generates a computer program, in a particular domain-specific language (DSL), which given each sample input returns the matching output. A key element is being able to perform an efficient search in the space of valid programs. Here, we suggest a variant of MCTS that leads to state of the art results on two vastly different DSLs. The exploration method we propose includes multiple contributions: a modified visit count, a preprocessing procedure for the training dataset, and encoding the part of the program that was already executed.
@article{arxiv.2303.07166,
title = {Improved Tree Search for Automatic Program Synthesis},
author = {Aran Carmon and Lior Wolf},
journal= {arXiv preprint arXiv:2303.07166},
year = {2023}
}
Comments
Proceedings of the 2nd Exploration in Reinforcement Learning Workshop at the 36th International Conference on Machine Learning, 2019