Deep Q Learning in Stabilization of Inverted Pendulum
S. Suganthi Amudhan1, Bhavin Sedani2, Ved Vyas Dwivedi3

1S.Suganthi Amudhan*, Electronics and Communication Engineering, C.U.Shah University, Surendranagar, Gujarat, India.
2Dr.Bhavin Sedani, Electronics and Communication Engineering, L.D. College of Engineering, Ahmedabad, Gujarat, India.
3Dr.Ved Vyas Dwivedi, Pro. Vice Chancellor, C U Shah University Wadhwan City, Surendranagar Gujarat, India.

Manuscript received on November 13, 2019. | Revised Manuscript received on 24 November, 2019. | Manuscript published on December 10, 2019. | PP: 803-807 | Volume-9 Issue-2, December 2019. | Retrieval Number: B6904129219/2019©BEIESP | DOI: 10.35940/ijitee.B6904.129219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Reinforcement Learning is a concept in which an agent takes actions in an environment to maximize its aggregate reward. Agents in Reinforcement Learning algorithms are penalized for bad actions and rewarded for good ones. Deep Reinforcement learning is used to overcome some shortcomings in Reinforcement learning like lack of variety in the open source collection and change in task’s difficulty based on reward or set of actions. In a larger environment, inference of new states from already explored states is a difficult task due to its time & space complexity. Hence the Q-value function which represents the quality value is approximated by Deep Q-learning that uses a neural network for the same. The results of implementing Deep Q Learning (DQN), Double DQN, Dueling DQN, Noisy DQN & DQN Prioritized Experience Replay techniques & their performance in stabilization of inverted pendulum are highlighted in this paper. Deep Reinforcement learning can be applied in various platform like for recognition, perception in computer vision, for simulation to real robot control in robotics, for sequence generation, translation in Natural Language processing, for Poker, Bridge StarCraft in games, for pricing, trading risk management in finance, for e- commerce, customer management in business management, for diagnosis using Electronic Medical Records in healthcare and in adaptive decision control. 
Keywords:  Deep Q Learning, Inverted Pendulum, OpenAI gym, Reinforcement Learning, Deep Reinforcement Learning
Scope of the Article: Learning Deep