Intelligent control system with reinforcement learning for solving video game tasks
dc.contributor.author | Osypenko, M. | |
dc.contributor.author | Shymkovych, V. | |
dc.contributor.author | Kravets, P. | |
dc.contributor.author | Novatsky, A. | |
dc.contributor.author | Shymkovych, L. | |
dc.date.accessioned | 2024-11-12T10:27:55Z | |
dc.date.available | 2024-11-12T10:27:55Z | |
dc.date.issued | 2024 | |
dc.description.abstract | This paper describes the development of a way to represent the state and build appropriate deep learning models to effectively solve reinforcement learning video game tasks. It has been demonstrated in the Battle City video game environment that careful design of the state functions can produce much better results without changes to the reinforcement learning algorithm, significantly speed up learning, and enable the agent to generalize and solve previously unknown levels. The agent was trained for 200 million epochs. Further training did not improve results. Final results reach 75% win rate in the first level of Battle City. In most of the 25% of games lost, the agent fails because it chooses the wrong path to pursue an enemy that is closer to the base and therefore slower. The reason for this is the limitation of cartographic information. To further improve performance and possibly achieve 100% win rate, it is recommended to find a way to effectively include full information about walls and other map objects. The developed method can be used to improve performance in real applications. | |
dc.format.pagerange | С. 34-46 | |
dc.identifier.citation | Intelligent control system with reinforcement learning for solving video game tasks / M. Osypenko, V. Shymkovych, P. Kravets, A. Novatsky, L. Shymkovych // Адаптивні системи автоматичного управління : міжвідомчий науково-технічний збірник. – 2024. – № 2 (45). – С. 34-46. – Бібліогр.: 25 назв. | |
dc.identifier.uri | https://ela.kpi.ua/handle/123456789/70505 | |
dc.language.iso | en | |
dc.publisher | КПІ ім. Ігоря Сікорського | |
dc.publisher.place | Київ | |
dc.rights.uri | https://creativecommons.ru/licenses | |
dc.source | Адаптивні системи автоматичного управління : міжвідомчий науково-технічний збірник, № 2 (45), 2024 | |
dc.subject | reinforcement learning | |
dc.subject | deep learning | |
dc.subject | state representation | |
dc.subject | neural network | |
dc.subject | Battle City | |
dc.subject.udc | 004.89, 004.912 | |
dc.title | Intelligent control system with reinforcement learning for solving video game tasks | |
dc.type | Article |
Файли
Контейнер файлів
1 - 1 з 1
Ліцензійна угода
1 - 1 з 1
Ескіз недоступний
- Назва:
- license.txt
- Розмір:
- 8.98 KB
- Формат:
- Item-specific license agreed upon to submission
- Опис: