| 查看: 996 | 回复: 4 | |||
| 【有奖交流】积极回复本帖子，参与交流，就有机会分得作者 yaoshunbo 的 6 个金币 ，回帖就立即获得 1 个金币，每人有 1 次机会 | |||
[交流]
欢迎引用
|
|||
|
摘要：Hybrid electric vehicles can achieve better fuel economy than conventional vehicles by utilizing multiple power sources. While these power sources have been controlled by rule-based or optimization-based control algorithms, recent studies have shown that machine learning-based con trol algorithms such as online Deep Reinforcement Learning (DRL) can effectively control the power sources as well. However, the optimization and training processes for the online DRL-based pow ertrain control strategy can be very time and resource intensive. In this paper, a new offline–online hybrid DRL strategy is presented where offline vehicle data are exploited to build an initial model and an online learning algorithm explores a new control policy to further improve the fuel economy. In this manner, it is expected that the agent can learn an environment consisting of the vehicle dynamics in a given driving condition more quickly compared to the online algorithms, which learn the optimal control policy by interacting with the vehicle model from zero initial knowledge. By incorporating a priori offline knowledge, the simulation results show that the proposed approach not only accelerates the learning process and makes the learning process more stable, but also leads to a better fuel economy compared to online only learning algorithms. 论文：With the advancements of data science, machine learning has become a vital tool for improving decision making by using raw data and information as input. Significant results can be seen by using different machine learning techniques in various real-world domains, such as cybersecurity systems, engineering, healthcare, e-commerce, agriculture, etc. [1] [1] Yao, Z.; Yoon, H.-S.; Hong, Y.-K. Control of Hybrid Electric Vehicle Powertrain Using Offline-Online Hybrid Reinforcement Learning. Energies 2023, 16, 652. https://doi.org/10.3390/en16020652 |
回复此楼» 猜你喜欢
售一区SCI文章T0P，我:8O.551.O54,科目全,可十急
已经有3人回复
-
售SCI一区T0P文章，我:8O.55.1.O.54,科目全,可伽急
已经有9人回复
-
时间戳今天，20号变了
已经有5人回复
-
2026国自然函评费到账
已经有9人回复
-
放榜前的不淡定
已经有14人回复
-
建议基金发布提前给出明确的时间点
已经有13人回复
-
今日不放榜？网传国自然预计 8 月 27 日可查结果
已经有20人回复
-
科研孤儿太难了
已经有18人回复
-
看来今天不会放榜了？
已经有11人回复
-
时间戳又变了
已经有19人回复
» 抢金币啦！回帖就可以得到:
-
告别流水线爽文！108万字完结仙侠《女娲石之灵石奇缘（仙界篇）》值得细品
+1/9029
-
基金申请小调查！预祝申请必定中中中！！祈福！！！
+5/370
-
坐标北京诚征男友
+1/112
-
山东征女友，坐标济南
+1/89
-
Polymers 期刊特刊 组稿
+1/79
-
焦虑
+1/70
-
哈尔滨工业大学（校本部）电子与信息工程学院2027级博士招生
+1/65
-
强耀生物金秋开学季活动，2026年8月18日-10月31日，肽库筛选低至2W5
+3/52
-
瑞典-博后-固态电池-粘结剂-锂离子电池方向
+1/37
-
南京理工大学优青团队催化化学方向招收推免研究生
+1/26
-
pcold 原核表达载体
+1/11
-
中科院大连化学物理研究所 招聘 催化剂研发方向 科研助理 2名
+1/6
-
南方医科大学深圳医院陈烨/余涛教授课题组联合培养博士后招聘
+1/6
-
找女友
+1/5
-
清华大学联培学生/科研助理/研究实习生招聘
+1/5
-
河海大学海洋环境污染与生态毒理学研究组招收2027级硕士生 及博士研究生
+1/2
-
清华大学环境课题组招聘环境工作专业客座生研究生2-3名（应用导向）
+1/2
-
新审查指南施行半年，AI方向的专利申请是不是更看"技术味"了？
+1/2
-
清华大学环境课题组招聘环境工作专业客座生研究生2-3名（应用导向）
+1/1
-
厦门大学郑靖课题组招收光学材料方向博士研究生及博士后
+1/1
★
yaoshunbo(金币+1): 谢谢参与
yaoshunbo(金币+1): 谢谢参与
|
本帖内容被屏蔽 |
4楼2023-04-19 15:43:05
简单回复
tzynew2楼
2023-02-28 21:45
回复
yaoshunbo(金币+1): 谢谢参与
2023-02-28 21:53
回复
yaoshunbo(金币+1): 谢谢参与
XG-WUST5楼
2023-04-24 18:44
回复
yaoshunbo(金币+1): 谢谢参与
up 发自小木虫IOS客户端
