2836-7863ISSN (Online)
Volume 3 , Issue 2 , PP: 9-17, 2024 | Cite this article as | XML | Html | PDF | Full Length Article
Talal Markabi 1 * , Bahaa Mansoura 2
Doi: https://doi.org/10.54216/NIF.030202
The Q learning algorithm in reinforcement learning is one of the algorithms that allows the robot to learn the surrounding environment without the need for prior training samples with the principle of reward and punishment for the robot through interaction with the environment. Increasing the number of hidden layers of the deep neural network used and adjusting some of the higher parameters in it can increase the reward of the robot and thus obtain the best path to achieve the goal.
Neural network , Deep learning , Robotics , Layers
[1] Mnih ,V., Kavukcuoglu,K., Silver,D., Graves,A., Antonoglou,L., Wierstra,D., Riedmiller,M.(2013). Playing Atari with Deep Reinforcement Learning: DeepMind Technologies. deepmind.com.
[2] NAEEM ,M., RIZVI,S., CORONATO, A. (2020) .Gentle Introduction to Reinforcement Learning and Its Application in Different Fields: Digital Object Identifier 10.1109/ACCESS.
[3] Aradi, S., Becsi,T., Gaspar,P.(2018). Policy Gradient based Reinforcement Learning Approach for Autonomous Highway Driving: IEEE Conference on Control Technology and Applications (CCTA) Copenhagen, Denmark, August.
[4] Doltsinis, S., Ferreira, P., Lohse,N.(2014) .An MDP Model-Based Reinforcement Learning Approach for Production Station Ramp-Up Optimization: Q-Learning Analysis: IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS: SYSTEMS, VOL. SEPTEMBER.
[5] Ronecker,M., Zhu ,Y.(2019).Deep Q-Network Based Decision Making for Autonomous Driving :2019 3rd IEEE International Conference on Robotics and Automation Sciences.
[6] Saini,A. , Gupta,T., Kumar,R., Gupta ,A., Panwar, M., Mittal, A.(2017). Image based Indian Monument Recognition using Convoluted Neural Networks: 2017 International Conference on Big Data, IoT and Data Science (BID) Vishwakarma Institute of Technology, Pune,
[7] Zohrer,M., Pernkopf,F.(2018). Heart Sound Segmentation – An Event Detection Approach using Deep Recurrent Neural Networks: Citation information: DOI 10.1109/TBME.2018.2843258, IEEE Transactions on Biomedical Engineering.
[8] Donoghue,B., Osband,I., Munos,R., Mnih,V.(2018). The Uncertainty Bellman Equation and Exploration: arXiv: 1709. 05380 v4 [cs.AI].
[9] Andrew, Ng.(2017). Machine Learning: Stanford university, http://cnx.org/content/col11500/1.4/.
[10] Rao,R., Narasimhan,K.(2020) .Stage Epsilon-Greedy Exploration for Reinforcement Learning: Princeton University, Department of Computer Science.
