Reinforcement Learning for Integer Programming: Learning to Cut
ICML 2020, 2019.
The variety of tasks across which the reinforcement learning agent is demonstrated to generalize without being trained for, provides convincing evidence that it is able to learn an intelligent algorithm for selecting cutting planes
Integer programming (IP) is a general optimization framework widely applicable to a variety of unstructured and structured problems arising in, e.g., scheduling, production planning, and graph optimization. As IP models many provably hard to solve problems, modern IP solvers rely on many heuristics. These heuristics are usually human-de...More
PPT (Upload PPT)