BriefGPT.xyz
Jun, 2023
TreeDQN:学习最小化分枝定界树
TreeDQN: Learning to minimize Branch-and-Bound tree
HTML
PDF
Dmitry Sorokin, Alexander Kostin
TL;DR
本文介绍了一种基于强化学习的组合优化问题解决方法,使用树马尔可夫决策过程视角选择变量分支,并且优化学习对象,相较之前的强化学习方法,训练数据量更小,生成树的大小更小。
Abstract
combinatorial optimization
problems require an exhaustive search to find the optimal solution. A convenient approach to solving
combinatorial optimization
tasks in the form of
→