Reinforcement Learning and Data-Generation for Syntax-Guided Synthesis

Julian Parsert, Elizabeth Polgreen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Program synthesis is the task of automatically generating code based on a specification. In Syntax-Guided Synthesis (SyGuS) this specification is a combination of a syntactic template and a logical formula, and the result is guaranteed to satisfy both. We present a reinforcement-learning guided algorithm for SyGuS which uses Monte-Carlo Tree Search (MCTS) to search the space of candidate solutions. Our algorithm learns policy and value functions which, combined with the upper confidence bound for trees, allow it to balance exploration and exploitation. A common challenge in applying machine learning approaches to syntax-guided synthesis is the scarcity of training data. To address this, we present a method for automatically generating training data for SyGuS based on anti-unification of existing first-order satisfiability problems, which we use to train our MCTS policy. We implement and evaluate this setup and demonstrate that learned policy and value improve the synthesis performance over a baseline by over 26 percentage points in the training and testing sets. Our tool outperforms state-of-the-art tool cvc5 on the training set and performs comparably in terms of the total number of problems solved on the testing set (solving 23% of the benchmarks on which cvc5 fails). We make our data set publicly available, to enable further application of machine learning methods to the SyGuS problem.
Original languageEnglish
Title of host publicationThe 38th Annual AAAI Conference on Artificial Intelligence
Subtitle of host publicationAAAI Technical Track on Knowledge Representation and Reasoning
PublisherAAAI Press
Pages10670-10678
Number of pages9
Volume38
Edition9
ISBN (Electronic)9781577358879
DOIs
Publication statusPublished - 24 Mar 2024
Event38th Annual AAAI Conference on Artificial Intelligence - Vancouver, Canada
Duration: 20 Feb 202427 Feb 2024
Conference number: 38
https://aaai.org/

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
PublisherAAAI Press
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

Conference38th Annual AAAI Conference on Artificial Intelligence
Abbreviated titleAAAI 2024
Country/TerritoryCanada
Period20/02/2427/02/24
Internet address

Fingerprint

Dive into the research topics of 'Reinforcement Learning and Data-Generation for Syntax-Guided Synthesis'. Together they form a unique fingerprint.

Cite this