On the Effect of the Layers’ Number of Deep Neural Network for Improving the Reward of a Reinforcement Learning Robot

aspg-39-3057-1792222540 20261017073540 American Scientific Publishing Group admin@americaspg.com American Scientific Publishing Group Neutrosophic and Information Fusion NIF 2836-7863 2024 3 2 On the Effect of the Layers’ Number of Deep Neural Network for Improving the Reward of a Reinforcement Learning Robot Talal Markabi Faculty of Informatics Engineering, Albaath University, Syria Bahaa Mansoura Faculty of Informatics Engineering, Albaath University, Syria 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, using the principle of reward and punishment through interaction with the environment. Increasing the number of hidden layers of the deep neural network and adjusting some of its hyperparameters can increase the robot’s reward and thus obtain the best path to achieve the goal. 2024 07 11 3057 https://creativecommons.org/licenses/by/4.0/ 10.54216/NIF.030202 https://americaspg.com/journal/39/article/3057 https://americaspg.com/storage/articles/manuscripts/01M3T7S2P4JWX34F54FKZ19NGG.pdf