DeepAI AI Chat
Log In Sign Up

Improving SAT Solver Heuristics with Graph Networks and Reinforcement Learning

by   Vitaly Kurin, et al.
University of Oxford

We present GQSAT, a branching heuristic in a Boolean SAT solver trained with value-based reinforcement learning (RL) using Graph Neural Networks for function approximation. Solvers using GQSAT are complete SAT solvers that either provide a satisfying assignment or a proof of unsatisfiability, which is required for many SAT applications. The branching heuristic commonly used in SAT solvers today suffers from bad decisions during their warm-up period, whereas GQSAT has been trained to examine the structure of the particular problem instance to make better decisions at the beginning of the search. Training GQSAT is data efficient and does not require elaborate dataset preparation or feature engineering to train. We train GQSAT on small SAT problems using RL interfacing with an existing SAT solver. We show that GQSAT is able to reduce the number of iterations required to solve SAT problems by 2-3X, and it generalizes to unsatisfiable SAT instances, as well as to problems with 5X more variables than it was trained on. We also show that, to a lesser extent, it generalizes to SAT problems from different domains by evaluating it on graph coloring. Our experiments show that augmenting SAT solvers with agents trained with RL and graph neural networks can improve performance on the SAT search problem.


Learning a SAT Solver from Single-Bit Supervision

We present NeuroSAT, a message passing neural network that learns to sol...

Enhancing SAT solvers with glue variable predictions

Modern SAT solvers routinely operate at scales that make it impractical ...

Learning Branching Heuristics for Propositional Model Counting

Propositional model counting or #SAT is the problem of computing the num...

Symbiosis of Search and Heuristics for Random 3-SAT

When combined properly, search techniques can reveal the full potential ...

Learning and Optimization of Blackbox Combinatorial Solvers in Neural Networks

The use of blackbox solvers inside neural networks is a relatively new a...

NeuroComb: Improving SAT Solving with Graph Neural Networks

Propositional satisfiability (SAT) is an NP-complete problem that impact...

MatSat: a matrix-based differentiable SAT solver

We propose a new approach to SAT solving which solves SAT problems in ve...