<ul><li>Mixed Integer Linear Program (MILP) solvers heavily rely on hand-crafted heuristics for branching.</li><li>Data-driven approaches have been used to automatically learn these heuristics.</li><li>Suboptimal-Demonstration-Guided Reinforcement Learning (SORREL) is proposed to learn branching using suboptimal demonstrations.</li><li>SORREL shows advanced performance in branching quality and training efficiency for various MILPs.</li></ul>

SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch

Discover more