arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2110.03595cs.LGcs.AI
收藏

基于等方差和局部搜索的TSP问题的深度RL推广

Generalization in Deep RL for TSP Problems via Equivariance and Local Search

University of Michigan(密歇根大学);Shanghai Jiao Tong University(上海交通大学)

Wenbin Ouyang, Yisen Wang, Paul Weng, Shaochen Han

摘要:

深度强化学习(RL)已被证明是解决旅行商问题(TSP)的小规模实例的有竞争力的启发式算法,但其在大规模实例上的性能不足。由于在大型实例上进行训练是不切实际的,我们设计了一种新的深度RL方法,重点是泛化能力。我们的主张由一个简单的深度学习架构组成,该架构使用新颖的RL训练技术进行学习,利用了两个主要思想。首先,我们利用等方差来促进训练。其次,我们将高效的局部搜索算法与通常的RL训练相结合,以平滑价值景观。为了验证整个方法,我们根据相关的最先进的深度RL方法对随机和现实TSP问题进行了实证评估。此外,我们提出了一个消融研究,以了解其每个组成部分的贡献

英文摘要:

Deep reinforcement learning (RL) has proved to be a competitive heuristic for solving small-sized instances of traveling salesman problems (TSP), but its performance on larger-sized instances is insufficient. Since training on large instances is impractical, we design a novel deep RL approach with a focus on generalizability. Our proposition consisting of a simple deep learning architecture that learns with novel RL training techniques, exploits two main ideas. First, we exploit equivariance to facilitate training. Second, we interleave efficient local search heuristics with the usual RL training to smooth the value landscape. In order to validate the whole approach, we empirically evaluate our proposition on random and realistic TSP problems against relevant state-of-the-art deep RL methods. Moreover, we present an ablation study to understand the contribution of each of its component

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑