A Reinforcement Learning Method Based on an Improved Sampling Mechanism for Unmanned Aerial Vehicle Penetration
The penetration of unmanned aerial vehicles (UAVs) is an important aspect of UAV games. In recent years, UAV penetration has generally been solved using artificial intelligence methods such as reinforcement learning. However, the high sample demand of the reinforcement learning method poses a signif...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/10/7/642 |
| _version_ | 1797590743983849472 |
|---|---|
| author | Yue Wang Kexv Li Xing Zhuang Xinyu Liu Hanyu Li |
| author_facet | Yue Wang Kexv Li Xing Zhuang Xinyu Liu Hanyu Li |
| author_sort | Yue Wang |
| collection | DOAJ |
| description | The penetration of unmanned aerial vehicles (UAVs) is an important aspect of UAV games. In recent years, UAV penetration has generally been solved using artificial intelligence methods such as reinforcement learning. However, the high sample demand of the reinforcement learning method poses a significant challenge specifically in the context of UAV games. To improve the sample utilization in UAV penetration, this paper innovatively proposes an improved sampling mechanism called task completion division (TCD) and combines this method with the soft actor critic (SAC) algorithm to form the TCD-SAC algorithm. To compare the performance of the TCD-SAC algorithm with other related baseline algorithms, this study builds a dynamic environment, a UAV game, and conducts training and testing experiments in this environment. The results show that among all the algorithms, the TCD-SAC algorithm has the highest sample utilization rate and the best actual penetration results, and the algorithm has a good adaptability and robustness in dynamic environments. |
| first_indexed | 2024-03-11T01:24:50Z |
| format | Article |
| id | doaj.art-c40ce32ee61744eeb86cb440dd991e15 |
| institution | Directory Open Access Journal |
| issn | 2226-4310 |
| language | English |
| last_indexed | 2024-03-11T01:24:50Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj.art-c40ce32ee61744eeb86cb440dd991e152023-11-18T17:51:12ZengMDPI AGAerospace2226-43102023-07-0110764210.3390/aerospace10070642A Reinforcement Learning Method Based on an Improved Sampling Mechanism for Unmanned Aerial Vehicle PenetrationYue Wang0Kexv Li1Xing Zhuang2Xinyu Liu3Hanyu Li4School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, ChinaThe penetration of unmanned aerial vehicles (UAVs) is an important aspect of UAV games. In recent years, UAV penetration has generally been solved using artificial intelligence methods such as reinforcement learning. However, the high sample demand of the reinforcement learning method poses a significant challenge specifically in the context of UAV games. To improve the sample utilization in UAV penetration, this paper innovatively proposes an improved sampling mechanism called task completion division (TCD) and combines this method with the soft actor critic (SAC) algorithm to form the TCD-SAC algorithm. To compare the performance of the TCD-SAC algorithm with other related baseline algorithms, this study builds a dynamic environment, a UAV game, and conducts training and testing experiments in this environment. The results show that among all the algorithms, the TCD-SAC algorithm has the highest sample utilization rate and the best actual penetration results, and the algorithm has a good adaptability and robustness in dynamic environments.https://www.mdpi.com/2226-4310/10/7/642UAV penetrationreinforcement learningsample utilizationtask completion division |
| spellingShingle | Yue Wang Kexv Li Xing Zhuang Xinyu Liu Hanyu Li A Reinforcement Learning Method Based on an Improved Sampling Mechanism for Unmanned Aerial Vehicle Penetration Aerospace UAV penetration reinforcement learning sample utilization task completion division |
| title | A Reinforcement Learning Method Based on an Improved Sampling Mechanism for Unmanned Aerial Vehicle Penetration |
| title_full | A Reinforcement Learning Method Based on an Improved Sampling Mechanism for Unmanned Aerial Vehicle Penetration |
| title_fullStr | A Reinforcement Learning Method Based on an Improved Sampling Mechanism for Unmanned Aerial Vehicle Penetration |
| title_full_unstemmed | A Reinforcement Learning Method Based on an Improved Sampling Mechanism for Unmanned Aerial Vehicle Penetration |
| title_short | A Reinforcement Learning Method Based on an Improved Sampling Mechanism for Unmanned Aerial Vehicle Penetration |
| title_sort | reinforcement learning method based on an improved sampling mechanism for unmanned aerial vehicle penetration |
| topic | UAV penetration reinforcement learning sample utilization task completion division |
| url | https://www.mdpi.com/2226-4310/10/7/642 |
| work_keys_str_mv | AT yuewang areinforcementlearningmethodbasedonanimprovedsamplingmechanismforunmannedaerialvehiclepenetration AT kexvli areinforcementlearningmethodbasedonanimprovedsamplingmechanismforunmannedaerialvehiclepenetration AT xingzhuang areinforcementlearningmethodbasedonanimprovedsamplingmechanismforunmannedaerialvehiclepenetration AT xinyuliu areinforcementlearningmethodbasedonanimprovedsamplingmechanismforunmannedaerialvehiclepenetration AT hanyuli areinforcementlearningmethodbasedonanimprovedsamplingmechanismforunmannedaerialvehiclepenetration AT yuewang reinforcementlearningmethodbasedonanimprovedsamplingmechanismforunmannedaerialvehiclepenetration AT kexvli reinforcementlearningmethodbasedonanimprovedsamplingmechanismforunmannedaerialvehiclepenetration AT xingzhuang reinforcementlearningmethodbasedonanimprovedsamplingmechanismforunmannedaerialvehiclepenetration AT xinyuliu reinforcementlearningmethodbasedonanimprovedsamplingmechanismforunmannedaerialvehiclepenetration AT hanyuli reinforcementlearningmethodbasedonanimprovedsamplingmechanismforunmannedaerialvehiclepenetration |