Reinforcement Learning and Data-Generation for Syntax-Guided Synthesis
This work addresses the challenge of automating code generation for program synthesis, which is incremental as it builds on existing SyGuS methods by integrating machine learning techniques.
The paper tackles the problem of program synthesis in Syntax-Guided Synthesis (SyGuS) by developing a reinforcement learning algorithm using Monte-Carlo Tree Search and a data-generation method to address training data scarcity, resulting in a 26 percentage point improvement over a baseline and competitive performance against state-of-the-art tool cvc5, solving 23% of benchmarks where cvc5 fails.
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.