RL based Differential Drive Primitive Policy for Transfer Learning / (Record no. 609005)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 01764nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 629.8 |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Shahid, Mahrukh |
| 245 ## - TITLE STATEMENT | |
| Title | RL based Differential Drive Primitive Policy for Transfer Learning / |
| Statement of responsibility, etc. | Mahrukh Shahid |
| 264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Place of production, publication, distribution, manufacture | Islamabad : |
| Name of producer, publisher, distributor, manufacturer | SMME- NUST; |
| Date of production, publication, distribution, manufacture, or copyright notice | 2022. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 52p. |
| Other physical details | Soft Copy |
| Dimensions | 30cm |
| 500 ## - GENERAL NOTE | |
| General note | To ensure the steady navigation for robot stable controls are the basic unit and control values<br/>selection is highly environment dependent. Adding Generalization to system is the key to<br/>reusability of control parameters to ensure adaptability in robots to perform with sophistication, in<br/>the environments about which they have no prior knowledge, for this Reinforcement Leaning (RL)<br/>based control systems are promising. However, tuning appropriate parameters to train RL<br/>algorithm is a challenge. Therefore, we designed a continuous reward function to minimizing the<br/>sparsity and stabilizes the policy convergence, to attain control generalization for differential drive<br/>robot. We Implemented Twin Delayed Deep Deterministic Policy Gradient-TD3 on Open-AI Gym<br/>Race Car. System was trained to achieve smart primitive control policy, moving forward in the<br/>direction of goal by maintaining an appropriate distance from walls to avoid collisions. Resulting<br/>policy was tested on unseen environments and observed precisely performing results. Upon<br/>comparative analysis of TD3 with DDPG, TD3 policy outperformed the DDPG policy in both<br/>training and testing phase, proving TD3 to be resource efficient and stable. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | MS Robotics and Intelligent Machine Engineering |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervisor : Dr. Yasar Ayaz |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="http://10.250.8.41:8080/xmlui/handle/123456789/30557">http://10.250.8.41:8080/xmlui/handle/123456789/30557</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Thesis |
| Withdrawn status | Permanent Location | Current Location | Shelving location | Date acquired | Full call number | Barcode | Koha item type |
|---|---|---|---|---|---|---|---|
| School of Mechanical & Manufacturing Engineering (SMME) | School of Mechanical & Manufacturing Engineering (SMME) | E-Books | 04/29/2024 | 629.8 | SMME-TH-757 | Thesis |