Nurulhidayati Haji Mohd Sani creator author. Somnuk Phon-Amnuaisuk, Prof advisors. Thien Wan Au, Dr. advisors. Universiti Teknologi Brunei text bx Bandar Seri Begawan Universiti Teknologi Brunei 2023 monographic eng

print

xvi, 148 pages : illustrations ; 30 cm. general Nurulhidayati Haji Mohd Sani Submitted in fulfillment of the requirements for the degree of Doctor of Philosophy. ABSTRACT Reinforcement learning (RL) is a machine learning technique that allows intelligent agents to learn a new task without being explicitly supervised. RL agents learn to perform a new task based on reinforcement signals. Traditional RL enumerates possible states (S) and associates actions (policy) to each state. The main disadvantage of traditional RL is that the process is slower in a larger and more complex environment. Also, many decision-making processes are involved in a complex environment instead of focusing on just one goal. In contrast to the traditional position-based approach, we investigate a visual-based Q-learning agent that uses the projection of rays to perceive its environ-ment. Despite the increasing number of possible state value inputs due to the number of angles between rays that the agent can perceive, or the increasing number of objects in the environment when this approach is used, it allows the agent greater flexibility in reusing its strategy in different environments. This flexibility is very useful, especially in a real-world application where the environment is known to be very dynamic. Our preliminary study allows our agent to use visual perception to navigate different environment sizes and settings. In our thesis, we also studied a Q-learning agent in a navigation problem with sub-goals using amplified feedback signals to determine the most effective strategies for amplification signals to solve the problem. We investigated these signals using two different problem configurations: sequential sub-goals and non-sequential sub-goals. In the problem with sequential sub-goals, the agent is forced to reach the goal in a specific order to achieve the goal. In the problem with non-sequential sub-goals, the order of the goal is irrelevant but necessary to achieve the optimal reward. The results show that although the agent can learn and achieve the goal in most of the feedback signals, having consistent, incremental rewards and immediate rewards contribute most to the agent's performance in achieving the goal. Dissertation (Doctor of Philosophy) - Universiti Teknologi Brunei (2032) Includes bibliographical references. Universiti Teknologi Brunei Thesis Universiti Teknologi Brunei Final Year Report Dissertation, Academic Thesis writing Dissertation Universiti Teknologi Brunei Computing and Informatics UTB 120 REPORT, THESIS & DISSERTATION RTDS 410 Universiti Teknologi Brunei 260608 eng