Boolean Satisfiability via Imitation Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Zewei, Liu, Huan, Yu, Yuanhao, Chen, Jun, Xu, Xiangyu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917284975476736
author Zhang, Zewei
Liu, Huan
Yu, Yuanhao
Chen, Jun
Xu, Xiangyu
author_facet Zhang, Zewei
Liu, Huan
Yu, Yuanhao
Chen, Jun
Xu, Xiangyu
contents We propose ImitSAT, a branching policy for conflict-driven clause learning (CDCL) solvers based on imitation learning for the Boolean satisfiability problem (SAT). Unlike previous methods that predict instance-level signals to improve CDCL branching indirectly, or rely on reinforcement learning and insufficient CDCL information to enhance branching, ImitSAT learns from expert KeyTrace that collapses a full run into the sequence of surviving decisions. Replaying a KeyTrace on the same instance is nearly conflict-free, providing dense decision-level supervision and directly reducing propagations -- the dominant contributor to wall-clock time. This prefix-conditioned supervision enables ImitSAT to reproduce high-quality branches without exploration, yielding faster convergence, stable training, and seamless integration into CDCL. Extensive experiments demonstrate that ImitSAT reduces propagation counts and runtime, outperforming state-of-the-art learned approaches. We released the source code and trained model at https://github.com/zewei-Zhang/ImitSAT
format Preprint
id arxiv_https___arxiv_org_abs_2509_25411
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Boolean Satisfiability via Imitation Learning
Zhang, Zewei
Liu, Huan
Yu, Yuanhao
Chen, Jun
Xu, Xiangyu
Artificial Intelligence
Machine Learning
We propose ImitSAT, a branching policy for conflict-driven clause learning (CDCL) solvers based on imitation learning for the Boolean satisfiability problem (SAT). Unlike previous methods that predict instance-level signals to improve CDCL branching indirectly, or rely on reinforcement learning and insufficient CDCL information to enhance branching, ImitSAT learns from expert KeyTrace that collapses a full run into the sequence of surviving decisions. Replaying a KeyTrace on the same instance is nearly conflict-free, providing dense decision-level supervision and directly reducing propagations -- the dominant contributor to wall-clock time. This prefix-conditioned supervision enables ImitSAT to reproduce high-quality branches without exploration, yielding faster convergence, stable training, and seamless integration into CDCL. Extensive experiments demonstrate that ImitSAT reduces propagation counts and runtime, outperforming state-of-the-art learned approaches. We released the source code and trained model at https://github.com/zewei-Zhang/ImitSAT
title Boolean Satisfiability via Imitation Learning
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2509.25411