English

Improved Tree Search for Automatic Program Synthesis

Machine Learning 2023-03-14 v1 Programming Languages Software Engineering

Abstract

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.

Keywords

Cite

@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