Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories. (arXiv:2205.14345v2 [cs.LG] UPDATED)

Combinatorial optimisation problems framed as mixed integer linear programmes
(MILPs) are ubiquitous across a range of real-world applications. The canonical
branch-and-bound algorithm seeks to exactly solve MILPs by constructing a
search tree of increasingly constrained sub-problems. In practice, its solving
time performance is dependent on heuristics, such as the choice of the next
variable to constrain ('branching'). Recently, machine learning (ML) has
emerged as a promising paradigm for branching. However, prior works have
struggled to apply reinforcement learning (RL), citing …

arxiv learning lg reinforcement reinforcement learning retrospective