Learning of a task despite credit assignment problem using deep representation learning with less trials
عنوان مقاله: Learning of a task despite credit assignment problem using deep representation learning with less trials
شناسه ملی مقاله: ISME25_096
منتشر شده در بیست و پنجمین همایش سالانه مهندسی مکانیک در سال 1396
شناسه ملی مقاله: ISME25_096
منتشر شده در بیست و پنجمین همایش سالانه مهندسی مکانیک در سال 1396
مشخصات نویسندگان مقاله:
MohammadJavad Davari Dolatabadi - MSc Student, Department of Mechatronics Eng., Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran
Khalil Alipour - Assistant professor, Department of Mechatronics Eng., Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran
Alireza Hadi - Assistant professor, Department of Mechatronics Eng., Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran
خلاصه مقاله:
MohammadJavad Davari Dolatabadi - MSc Student, Department of Mechatronics Eng., Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran
Khalil Alipour - Assistant professor, Department of Mechatronics Eng., Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran
Alireza Hadi - Assistant professor, Department of Mechatronics Eng., Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran
In this paper, we present three new methods to accelerate thelearning of a task by deterministic policy gradient algorithm.We focus specifically on learning of a task, which has theCredit Assignment (CA) problem. A Reinforcement Learning(RL) agent is performing this task in high dimensional statespace.The main idea of this paper is to use latent variablesthat deep autoencoders provide, to make a better rewardingsystem. We show that using these new rewards helpstremendously to learn the task in the similar circumstances.The task chosen for the algorithm is Push Recovery (PR) in asimulated environment.
کلمات کلیدی: Deep Learning- Push Recovery- CreditAssignment Problem- Latent Variable- Rewarding System-Inverse Reinforcement Learning
صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/634616/