Diagram of the reinforcement learning architecture based on DDPG proposed in this paper.

<p>Diagram of the reinforcement learning architecture based on DDPG proposed in this paper.</p>

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Yulin Tian (1457986) (author)
مؤلفون آخرون:	Shuqing Liu (483316) (author), Lu Wei (508666) (author), Zhen Li (49109) (author), Shaohu Tang (20880484) (author), Yuchen Zhang (524816) (author), Tao Zhu (118644) (author)
منشور في:	2025
الموضوعات:	Biochemistry Microbiology Biotechnology Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> aiming perform fast computation overall traffic efficiency experimental results show deep reinforcement learning distance road sections distance intersection scenarios signal control process active control scheme key state prediction overflow prevention goal distance intersections scenario solution algorithm based distance intersections active control overflow prevention overflow state target scenario state space overflow index travel delay reward sparsity reward function prediction method paper proposes paper builds existing problems control ability actively sense
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

مواد مشابهة