MARC details
| 000 -LEADER |
|---|
| fixed length control field |
03459nam a22003137a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
260608t2023 bx a|||g |||| 00| 0 eng d |
| 020 ## - INTERNATIONAL STANDARD BOOK NUMBER |
|---|
| Qualifying information |
hardback |
| 040 ## - CATALOGING SOURCE |
|---|
| Original cataloging agency |
Universiti Teknologi Brunei |
| Language of cataloging |
eng |
| Transcribing agency |
UTB |
| 084 ## - BOOK Call Number |
|---|
| Classification number |
UTB 120 REPORT, THESIS & DISSERTATION |
| -- |
RTDS 410 |
| 100 1# - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Nurulhidayati Haji Mohd Sani |
| Relator term |
author. |
| 245 10 - TITLE STATEMENT |
|---|
| Title |
A study of feedback signal calibration in reinforcement learning with sub-goals / |
| Statement of responsibility, etc. |
Nurulhidayati Haji Mohd Sani |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) |
|---|
| Place of publication, distribution, etc. |
Bandar Seri Begawan : |
| Name of publisher, distributor, etc. |
Universiti Teknologi Brunei, |
| Date of publication, distribution, etc. |
2023. |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
xvi, 148 pages : |
| Other physical details |
illustrations ; |
| Dimensions |
30 cm. |
| 500 ## - GENERAL NOTE |
|---|
| General note |
Submitted in fulfillment of the requirements for the degree of Doctor of Philosophy. |
| 500 ## - GENERAL NOTE |
|---|
| General note |
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.<br/>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.<br/>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.<br/>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. |
| 502 ## - Dissertation Note |
|---|
| Dissertation Note |
Dissertation (Doctor of Philosophy) - Universiti Teknologi Brunei (2032) |
| 504 ## - Bibliography, Etc. Note |
|---|
| Bibliography, Etc. Note |
Includes bibliographical references. |
| 610 #4 - SUBJECT ADDED ENTRY--CORPORATE NAME |
|---|
| Corporate name or jurisdiction name as entry element |
Universiti Teknologi Brunei |
| Form subdivision |
Thesis |
| 610 #4 - SUBJECT ADDED ENTRY--CORPORATE NAME |
|---|
| Corporate name or jurisdiction name as entry element |
Universiti Teknologi Brunei |
| Form subdivision |
Final Year Report |
| 650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
Dissertation, Academic |
| 650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
Thesis writing |
| 650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
Dissertation Universiti Teknologi Brunei |
| 650 #4 - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
Computing and Informatics |
| 700 1# - ADDED ENTRY--PERSONAL NAME |
|---|
| Personal name |
Somnuk Phon-Amnuaisuk, Prof |
| Relator term |
advisors. |
| 700 1# - ADDED ENTRY--PERSONAL NAME |
|---|
| Personal name |
Thien Wan Au, Dr. |
| Relator term |
advisors. |
| 710 ## - ADDED ENTRY--CORPORATE NAME |
|---|
| Corporate name or jurisdiction name as entry element |
Universiti Teknologi Brunei |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
Local Classification |
| Koha item type |
Reports, Thesis & Dissertation Students |
| 998 ## - LOCAL CONTROL INFORMATION (RLIN) |
|---|
| Internal field |
Reports, Thesis & Dissertation |
| CC (RLIN) |
850582 : 002454 c.1 UTB |
| Internal field |
Universiti Teknologi Brunei |
