按年被提到
20162017 · 1 次2026
强化学习与智能体›进化策略与探索·arXiv:1611.09940 · cs.AI

Neural Combinatorial Optimization with Reinforcement Learning

Irwan Bello, Hieu Pham, Quoc V. Le, Mohammad Norouzi, Samy Bengio · 2016
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-01-06 · 最近 2018-02-12
2不同的人
2活跃月份
2讨论串
1,080被引(OpenAlex)
arXiv 摘要(候选层不写导读)

This paper presents a framework to tackle combinatorial optimization problems using neural networks and reinforcement learning. We focus on the traveling salesman problem (TSP) and train a recurrent network that, given a set of city coordinates, predicts a distribution over different city permutations. Using negative tour length as the reward signal, we optimize the parameters of the recurrent network using a policy gradient method. We compare learning the network parameters on a set of training graphs against learning them on individual test graphs. Despite the computational expense, without much engineering and heuristic designing, Neural Combinatorial Optimization achieves close to optimal results on 2D Euclidean graphs with up to 100 nodes. Applied to the KnapSack, another NP-hard problem, the same method obtains optimal solutions for instances with up to 200 items.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论sytelus · 2018-02

“These are the type of articles that makes HN worth looking in to every once in while:). The circuit routing is indeed worth $100M problem. And it's going to remain unsolved in classical sense because its NP-Hard. The reason this is very interesting problem is that basic version of the problem is fairly easy to specify: You are given bunch of polygons, e…”

Adventures in Autorouting (2017)原评论 ↗
被提交为 story · 1 次