A Study of Learning Search Approximation in Mixed Integer Branch and Bound: Node Selection in SCIP

In line with the growing trend of using machine learning to help solve combinatorial optimisation problems, one promising idea is to improve node selection within a mixed integer programming (MIP) branch-and-bound tree by using a learned policy. Previous work using imitation learning indicates the f...

Full description

Bibliographic Details

Published in:	AI
Main Authors:	Kaan Yilmaz, Neil Yorke-Smith
Format:	Article
Language:	English
Published:	MDPI AG 2021-04-01
Subjects:	mixed integer programming node selection machine learning approximate pruning imitation learning SCIP
Online Access:	https://www.mdpi.com/2673-2688/2/2/10