Comprehensive Study on Reinforcement Learning and Deep Reinforcement Learning Schemes
Authors:
- Mansoor Ahmed KhuhroMKMansoor Ahmed Khuhro
- Muhammad WaqasMWMuhammad Waqas
- Umair SaeedUSUmair Saeed
- Mehar Khan NiaziMNMehar Khan Niazi
Open Access
- 27 December 2024
- journal article
- Published by Sir Syed University of Engineering and Technology in Sir Syed University Research Journal of Engineering & Technology
- Vol. 14 (2) , 1-6
Abstract
Reinforcement learning (RL) has emerged as a powerful tool for creating artificial intelligence systems (AIS) and solving problems which require sequential decision-making. Reinforcement learning has achieved some impressive achievements in recent years, surpassing humans in a variety of areas. According to recent research, deep learning (DL) techniques are used with techniques of reinforcement learning to recognize meaningful identification for a problem regarding high dimensional raw data input & enough to solve artificial general intelligence (AGI). In addition to the main concepts, this paper highlights the intuition behind the use RL and deep Q-network (DQN) over other algorithms. In this research paper, different methods and details for dealing with reinforcement learning difficulties have been presented. Finally, various difficulties of the reinforcement learning have been addressed.Keywords
This publication has 31 references indexed in Scilit:
- Botnet attack detection in Internet of Things devices over cloud environment via machine learningConcurrency and Computation: Practice and Experience, 2021
- Financial fraud detection applying data mining techniques: A comprehensive review from 2009 to 2019Computer Science Review, 2021
- A Model for Artificial General Intelligence2020
- Support vector machine2020
- The emergence of deep learning: new opportunities for music and audio technologiesNeural Computing and Applications, 2019
- Neuroscience-Inspired Artificial IntelligenceNeuron, 2017
- Convolutional Neural Network2017
- Markov decision processesEuropean Journal of Operational Research, 1989
- Mean, variance, and probabilistic criteria in finite Markov decision processes: A reviewJournal of Optimization Theory and Applications, 1988
- A new look at Bellman's principle of optimalityJournal of Optimization Theory and Applications, 1986