BriefGPT.xyz
Nov, 2023
利用潜在空间搜索的组合优化与策略适应
Combinatorial Optimization with Policy Adaptation using Latent Space Search
HTML
PDF
Felix Chalumeau, Shikha Surana, Clement Bonnet, Nathan Grinsztajn, Arnu Pretorius...
TL;DR
使用强化学习构建基于启发式方法的优化算法,通过预训练具有多样性的策略分布来优化搜索过程,在三个经典问题上实现了更好的性能和泛化能力。
Abstract
combinatorial optimization
underpins many real-world applications and yet, designing performant algorithms to solve these complex, typically NP-hard, problems remains a significant research challenge.
reinforcement lear
→