Improved Tree Search for Automatic Program Synthesis
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 13 references that are in the map. First posted on arXiv 13 Mar 2023.
Builds on
6 of 13 references.
References · 6
- 2016DeepCoder: Learning to Write Programscited by 149
- 2018Leveraging Grammar and Reinforcement Learning for Neural Program Synthesiscited by 84
- 2018Neural-Guided Deductive Search for Real-Time Program Synthesis from Examplescited by 39
- 2018Automatic Program Synthesis of Long Programs with a Learned Garbage Collectorcited by 24
- 2017Neural Program Meta-Inductioncited by 23
- 2018Solving the Rubik's Cube Without Human Knowledgecited by 15
Built on by
Not cited yet.