首页|Findings from Anhui University Yields New Data on Computational Intelligence (A Deep Reinforcement Learning-based Adaptive Large Neighborhood Search for Capacit ated Electric Vehicle Routing Problems)
Findings from Anhui University Yields New Data on Computational Intelligence (A Deep Reinforcement Learning-based Adaptive Large Neighborhood Search for Capacit ated Electric Vehicle Routing Problems)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in Machine Learning - Computational Intelligence. According to news reporting out of Hefei , People's Republic of China, by NewsRx editors, research stated, "The Capacitat ed Electric Vehicle Routing Problem (CEVRP) poses a novel chAllenge within the Field of vehicle routing optimization, as it requires consideration of both custo mer service requirements and electric vehicle recharging schedules. In addressin g the CEVRP, Adaptive Large Neighborhood Search (ALNS) has garnered widespread a cclaim due to its remarkable adaptability and versatility." Funders for this research include National Natural Science Foundation of China ( NSFC), Natural Science Foundation of Anhui Province. Our news journalists obtained a quote from the research from Anhui University, " However, the original ALNS, using a weight-based scoring method, relies solely o n the past performances of operators to determine their weights, thereby failing to capture crucial information about the ongoing search process. Moreover, it o ften employs a fixed single charging strategy for the CEVRP, neglecting the pote ntial impact of alternative charging strategies on solution improvement. Therefo re, this study treats the selection of operators as a Markov Decision Process and introduces a novel approach based on Deep Reinforcement Learning (DRL) for ope rator selection. This approach enables adaptive selection of both destroy and re pair operators, alongside charging strategies, based on the current state of the search process. More specificAlly, a state extraction method is devised to extr act features not only from the problem itself but also from the solutions genera ted during the iterative process. AdditionAlly, a novel reward function is desig ned to guide the DRL network in selecting an appropriate operator portfolio for the CEVRP. Experimental results demonstrate that the proposed algorithm excels i n instances with fewer than 100 customers, achieving the best values in 7 out of 8 test instances."
HefeiPeople's Republic of ChinaAsiaComputational IntelligenceEmerging TechnologiesMachine LearningReinforcem ent LearningAnhui University
NETL
NSTL
