期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 34, 期 4, 页码 2133-2143出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2021.3105937
关键词
Optimization; Evolutionary computation; Heuristic algorithms; Search problems; Neural networks; Genetics; Urban areas; Attention mechanism; deep reinforcement learning (DRL); multi-objective learning; neural combinatorial optimization; neural evolutionary algorithm
This article introduces a method for optimizing deep reinforcement learning models using neural evolutionary algorithms to solve combinatorial optimization problems. The proposed end-to-end multi-objective neural evolutionary algorithm demonstrates competitive and robust performance on the classic travel salesman problem and knapsack problem, and also performs well in inference time.
There has been a recent surge of success in optimizing deep reinforcement learning (DRL) models with neural evolutionary algorithms. This type of method is inspired by biological evolution and uses different genetic operations to evolve neural networks. Previous neural evolutionary algorithms mainly focused on single-objective optimization problems (SOPs). In this article, we present an end-to-end multi-objective neural evolutionary algorithm based on decomposition and dominance (MONEADD) for combinatorial optimization problems. The proposed MONEADD is an end-to-end algorithm that utilizes genetic operations and rewards signals to evolve neural networks for different combinatorial optimization problems without further engineering. To accelerate convergence, a set of nondominated neural networks is maintained based on the notion of dominance and decomposition in each generation. In inference time, the trained model can be directly utilized to solve similar problems efficiently, while the conventional heuristic methods need to learn from scratch for every given test problem. To further enhance the model performance in inference time, three multi-objective search strategies are introduced in this work. Our experimental results clearly show that the proposed MONEADD has a competitive and robust performance on a bi-objective of the classic travel salesman problem (TSP), as well as Knapsack problem up to 200 instances. We also empirically show that the designed MONEADD has good scalability when distributed on multiple graphics processing units (GPUs).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据