کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6853062 | 1436976 | 2018 | 66 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Decentralized Reinforcement Learning of Robot Behaviors
ترجمه فارسی عنوان
تسریع تفکیک دفاعی از رفتارهای ربات
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
تقویت یادگیری، سیستم های چندگانه، کنترل انحرافی، ربات های مستقل، هوش مصنوعی توزیع شده،
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
هوش مصنوعی
چکیده انگلیسی
A multi-agent methodology is proposed for Decentralized Reinforcement Learning (DRL) of individual behaviors in problems where multi-dimensional action spaces are involved. When using this methodology, sub-tasks are learned in parallel by individual agents working toward a common goal. In addition to proposing this methodology, three specific multi agent DRL approaches are considered: DRL-Independent, DRL Cooperative-Adaptive (CA), and DRL-Lenient. These approaches are validated and analyzed with an extensive empirical study using four different problems: 3D Mountain Car, SCARA Real-Time Trajectory Generation, Ball-Dribbling in humanoid soccer robotics, and Ball-Pushing using differential drive robots. The experimental validation provides evidence that DRL implementations show better performances and faster learning times than their centralized counterparts, while using less computational resources. DRL-Lenient and DRL-CA algorithms achieve the best final performances for the four tested problems, outperforming their DRL-Independent counterparts. Furthermore, the benefits of the DRL-Lenient and DRL-CA are more noticeable when the problem complexity increases and the centralized scheme becomes intractable given the available computational resources and training time.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Artificial Intelligence - Volume 256, March 2018, Pages 130-159
Journal: Artificial Intelligence - Volume 256, March 2018, Pages 130-159
نویسندگان
David L. Leottau, Javier Ruiz-del-Solar, Robert Babuška,