- Title
- Deep reinforcement learning for cognitive radio and software-defined networks
- Creator
- Jalil, Syed Qaisar
- Relation
- University of Newcastle Research Higher Degree Thesis
- Resource Type
- thesis
- Date
- 2022
- Description
- Research Doctorate - Doctor of Philosophy (PhD)
- Description
- Reinforcement learning is a branch of machine learning that enables machines to learn by trial and error. It is an experience-driven sequential learning process to achieve a particular goal. Recent advances in reinforcement learning have combined deep learning, which has led to the emergence of a new field called deep reinforcement learning (DRL). DRL algorithms have shown great success on various complex decision-making tasks that were earlier thought to be extremely difficult for a computer. Communication networks play a fundamental role in today's information age, where connectivity has become a basic commodity of life. They will play an even more critical role in the future, when everything from people, animals, wearable devices, and cars to buildings and industries, will be connected. Providing connectivity on such a massive scale calls for an advanced set of solutions that can deal with complex, large-scale, and dynamic wireless and wired networks. DRL has the potential to meet these challenges due to its ability to learn from experience and adapt to the changing complex decision-making environment. Thus, we use DRL as a primary tool in this thesis and investigate one wireless and one wired technology.
- Subject
- deep reinforcement learning; cognitive radio networks; software-defined networks; framework
- Identifier
- http://hdl.handle.net/1959.13/1430830
- Identifier
- uon:38884
- Rights
- Copyright 2022 Syed Qaisar Jalil
- Language
- eng
- Full Text
- Hits: 5455
- Visitors: 4512
- Downloads: 243
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | ATTACHMENT01 | Thesis | 11 MB | Adobe Acrobat PDF | View Details Download | ||
| View Details Download | ATTACHMENT02 | Abstract | 497 KB | Adobe Acrobat PDF | View Details Download |