[1] Ravello, Zvi. Three Lectures on: Control of Coupled Fast and Slow Dynamics. Sept. 20AD, uma.ensta-paristech.fr/itn-sadco/talks/ravello2012/ravello2012_artstein.pdf.


[2] Oishi. “State Feedback.” 31 Mar. 2019, British Columbia.


[3] Pati, Jyoti Ranjan. Modeling, Identification and Control of Cart-Pole System. National Institude of Technology, Rourkela, May 2014, ethesis.nitrkl.ac.in/6302/1/E-64.pdf.


[4] Willy, Wojsznis K, and Belvins Terry. “Evolving PID Tuning Rules.” CE USA, 13 Mar. 2013, www.controleng.com/articles/evolving-pid-tuning-rules/.


[5] Foster, Corey. “Modern Updates in PID Control Tuning.” CE USA, 8 Aug. 2014, www.controleng.com/articles/modern-updates-in-pid-control-tuning/.


[6] Yu, Felix. “Deep Q Network vs Policy Gradients – An Experiment on VizDoom with Keras.” A Comprehensive Guide to Fine-Tuning Deep Learning Models in Keras (Part I) | Felix Yu, 12 Oct. 2017, flyyufelix.github.io/2017/10/12/dqn-vs-pg.html.


[7] “Q-Learning.” Wikipedia, Wikimedia Foundation, 27 Mar. 2019, en.wikipedia.org/wiki/Q-learning.


[8] OpenAI. “OpenGymAI.” Gym, gym.openai.com/.


[9] Surma, Greg. “Cartpole – Introduction to Reinforcement Learning (DQN – Deep Q-Learning).” Towards Data Science, Medium, 26 Sept. 2018, towardsdatascience.com/cartpole-introduction-to-reinforcement-learning-ed0eb5b58288.


[10] R. Sutton and A. G. Barto: Reinforcement learning: An introduction. Cambridge: MIT press, 1998.


[11]Tedrake, Russ. “Underactuated Robotics.” Underactuated Robotics, 2019, underactuated.csail.mit.edu/underactuated.html?chapter=acrobot.