Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning
Nowadays, the advancement of drones is also factored in the development of a world surrounded by technologies. One of the aspects emphasized here is the difficulty of controlling the drone, and the system developed is still under full control by the users as well. Reinforcement Learning is used to e...
| Principais autores: | , , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | English |
| Publicado em: |
semarak ilmu
2023
|
| Assuntos: | |
| Acesso em linha: | http://eprints.uthm.edu.my/10521/1/J16168_3519c3c49183a6f808613789cd52277b.pdf |
| _version_ | 1825638370992193536 |
|---|---|
| author | Mohamad Hafiz Abu Bakar, Mohamad Hafiz Abu Bakar Abu Ubaidah Shamsudin, Abu Ubaidah Shamsudin Ruzairi Abdul Rahim, Ruzairi Abdul Rahim Zubair Adil Soomro, Zubair Adil Soomro Andi Adrianshah, Andi Adrianshah |
| author_facet | Mohamad Hafiz Abu Bakar, Mohamad Hafiz Abu Bakar Abu Ubaidah Shamsudin, Abu Ubaidah Shamsudin Ruzairi Abdul Rahim, Ruzairi Abdul Rahim Zubair Adil Soomro, Zubair Adil Soomro Andi Adrianshah, Andi Adrianshah |
| author_sort | Mohamad Hafiz Abu Bakar, Mohamad Hafiz Abu Bakar |
| collection | UTHM |
| description | Nowadays, the advancement of drones is also factored in the development of a world surrounded by technologies. One of the aspects emphasized here is the difficulty of controlling the drone, and the system developed is still under full control by the users as well. Reinforcement Learning is used to enable the system to operate automatically, thus drone will learn the next movement based on the interaction between the agent and the environment. Through this study, Q-Learning and State-Action-Reward-StateAction (SARSA) are used in this study and the comparison of results involving both the performance and effectiveness of the system based on the simulation of both methods can be seen through the analysis. A comparison of both Q-learning and State-ActionReward-State-Action (SARSA) based systems in autonomous drone application was performed for evaluation in this study. According to this simulation process is shows
that Q-Learning is a better performance and effective to train the system to achieve desire compared with SARSA algorithm for drone controller. |
| first_indexed | 2024-03-05T22:05:46Z |
| format | Article |
| id | uthm.eprints-10521 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | English |
| last_indexed | 2024-03-05T22:05:46Z |
| publishDate | 2023 |
| publisher | semarak ilmu |
| record_format | dspace |
| spelling | uthm.eprints-105212024-01-03T01:34:46Z http://eprints.uthm.edu.my/10521/ Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning Mohamad Hafiz Abu Bakar, Mohamad Hafiz Abu Bakar Abu Ubaidah Shamsudin, Abu Ubaidah Shamsudin Ruzairi Abdul Rahim, Ruzairi Abdul Rahim Zubair Adil Soomro, Zubair Adil Soomro Andi Adrianshah, Andi Adrianshah T Technology (General) Nowadays, the advancement of drones is also factored in the development of a world surrounded by technologies. One of the aspects emphasized here is the difficulty of controlling the drone, and the system developed is still under full control by the users as well. Reinforcement Learning is used to enable the system to operate automatically, thus drone will learn the next movement based on the interaction between the agent and the environment. Through this study, Q-Learning and State-Action-Reward-StateAction (SARSA) are used in this study and the comparison of results involving both the performance and effectiveness of the system based on the simulation of both methods can be seen through the analysis. A comparison of both Q-learning and State-ActionReward-State-Action (SARSA) based systems in autonomous drone application was performed for evaluation in this study. According to this simulation process is shows that Q-Learning is a better performance and effective to train the system to achieve desire compared with SARSA algorithm for drone controller. semarak ilmu 2023 Article PeerReviewed text en http://eprints.uthm.edu.my/10521/1/J16168_3519c3c49183a6f808613789cd52277b.pdf Mohamad Hafiz Abu Bakar, Mohamad Hafiz Abu Bakar and Abu Ubaidah Shamsudin, Abu Ubaidah Shamsudin and Ruzairi Abdul Rahim, Ruzairi Abdul Rahim and Zubair Adil Soomro, Zubair Adil Soomro and Andi Adrianshah, Andi Adrianshah (2023) Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning. Journal of Advanced Research in Fluid Mechanics and Thermal Sciences, 30 (3). pp. 69-78. ISSN 2462-1943 https://doi.org/10.37934/araset.30.3.6978 |
| spellingShingle | T Technology (General) Mohamad Hafiz Abu Bakar, Mohamad Hafiz Abu Bakar Abu Ubaidah Shamsudin, Abu Ubaidah Shamsudin Ruzairi Abdul Rahim, Ruzairi Abdul Rahim Zubair Adil Soomro, Zubair Adil Soomro Andi Adrianshah, Andi Adrianshah Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning |
| title | Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning |
| title_full | Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning |
| title_fullStr | Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning |
| title_full_unstemmed | Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning |
| title_short | Comparison Method Q-Learning and SARSA for Simulation of Drone Controller using Reinforcement Learning |
| title_sort | comparison method q learning and sarsa for simulation of drone controller using reinforcement learning |
| topic | T Technology (General) |
| url | http://eprints.uthm.edu.my/10521/1/J16168_3519c3c49183a6f808613789cd52277b.pdf |
| work_keys_str_mv | AT mohamadhafizabubakarmohamadhafizabubakar comparisonmethodqlearningandsarsaforsimulationofdronecontrollerusingreinforcementlearning AT abuubaidahshamsudinabuubaidahshamsudin comparisonmethodqlearningandsarsaforsimulationofdronecontrollerusingreinforcementlearning AT ruzairiabdulrahimruzairiabdulrahim comparisonmethodqlearningandsarsaforsimulationofdronecontrollerusingreinforcementlearning AT zubairadilsoomrozubairadilsoomro comparisonmethodqlearningandsarsaforsimulationofdronecontrollerusingreinforcementlearning AT andiadrianshahandiadrianshah comparisonmethodqlearningandsarsaforsimulationofdronecontrollerusingreinforcementlearning |