Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


Thesis_Zhaoyuan_Yang.pdf (3.47 MB)

ETD Abstract Container

Abstract Header

Adversarial Reinforcement Learning for Control System Design: A Deep Reinforcement Learning Approach

Yang, Zhaoyuan, Yang
http://rave.ohiolink.edu/etdc/view?acc_num=osu152411491981452

Abstract Details

2018, Master of Science, Ohio State University, Electrical and Computer Engineering.
We adapt idea of adversarial reinforcement learning to numerical state inputs of controllers. We propose an idea of generating adversarial noises for inputs of controllers using deep reinforcement learning. We also propose an idea of using reinforcement learning agent as observer and using observer to reduce effect of adversarial noise. Idea of using reinforcement learning as observer may be helpful for adapting knowledge from simulation to real world. We performed a sequence of analyses about adversarial reinforcement learning and deep reinforcement learning. Through analysis, we discover deep reinforcement learning agent learnt in ideal environment is not robust to adversarial noise and learning in adversarial environment will make agent robust in both adversarial and non-adversarial environment. We make several conjectures about phenomena we observe, and propose an idea of how to let deep reinforcement learning agent better use state information. We also propose an idea of how to use neural network to find policies optimize cost objective automatically. In the end, we discuss possible works could be done in the future.
Abhishek Gupta (Advisor)
Wei Zhang (Committee Member)
74 p.
Artificial Intelligence; Computer Science; Electrical Engineering; Engineering
deep reinforcement learning; control system; adversarial reinforcement learning; machine learning

Recommended Citations

Citations

  • Yang, Yang, Z. (2018). Adversarial Reinforcement Learning for Control System Design: A Deep Reinforcement Learning Approach [Master's thesis, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu152411491981452

    APA Style (7th edition)

  • Yang, Yang, Zhaoyuan. Adversarial Reinforcement Learning for Control System Design: A Deep Reinforcement Learning Approach. 2018. Ohio State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu152411491981452.

    MLA Style (8th edition)

  • Yang, Yang, Zhaoyuan. "Adversarial Reinforcement Learning for Control System Design: A Deep Reinforcement Learning Approach." Master's thesis, Ohio State University, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=osu152411491981452

    Chicago Manual of Style (17th edition)

osu152411491981452
1,756
© 2018, some rights reserved.Creative Commons License Adversarial Reinforcement Learning for Control System Design: A Deep Reinforcement Learning Approach by Zhaoyuan Yang Yang is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License. Based on a work at etd.ohiolink.edu.
This open access ETD is published by The Ohio State University and OhioLINK.