Intelligent Game Strategies in Target-Missile-Defender Engagement Using Curriculum-Based Deep Reinforcement Learning
Aiming at the attack and defense game problem in the target-missile-defender three-body confrontation scenario, intelligent game strategies based on deep reinforcement learning are proposed, including an attack strategy applicable to attacking missiles and active defense strategy applicable to a tar...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/10/2/133 |
| _version_ | 1797623042806906880 |
|---|---|
| author | Xiaopeng Gong Wanchun Chen Zhongyuan Chen |
| author_facet | Xiaopeng Gong Wanchun Chen Zhongyuan Chen |
| author_sort | Xiaopeng Gong |
| collection | DOAJ |
| description | Aiming at the attack and defense game problem in the target-missile-defender three-body confrontation scenario, intelligent game strategies based on deep reinforcement learning are proposed, including an attack strategy applicable to attacking missiles and active defense strategy applicable to a target/defender. First, based on the classical three-body adversarial research, the reinforcement learning algorithm is introduced to improve the purposefulness of the algorithm training. The action spaces the reward and punishment conditions of both attack and defense confrontation are considered in the reward function design. Through the analysis of the sign of the action space and design of the reward function in the adversarial form, the combat requirements can be satisfied in both the missile and target/defender training. Then, a curriculum-based deep reinforcement learning algorithm is applied to train the agents and a convergent game strategy is obtained. The simulation results show that the attack strategy of the missile can maneuver according to the battlefield situation and can successfully hit the target after avoiding the defender. The active defense strategy enables the less capable target/defender to achieve the effect similar to a network adversarial attack on the missile agent, shielding targets from attack against missiles with superior maneuverability on the battlefield. |
| first_indexed | 2024-03-11T09:18:49Z |
| format | Article |
| id | doaj.art-49c5aaadbf324de887245e09ba8a6da8 |
| institution | Directory Open Access Journal |
| issn | 2226-4310 |
| language | English |
| last_indexed | 2024-03-11T09:18:49Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj.art-49c5aaadbf324de887245e09ba8a6da82023-11-16T18:27:02ZengMDPI AGAerospace2226-43102023-01-0110213310.3390/aerospace10020133Intelligent Game Strategies in Target-Missile-Defender Engagement Using Curriculum-Based Deep Reinforcement LearningXiaopeng Gong0Wanchun Chen1Zhongyuan Chen2School of Astronautics, Beihang University, Beijing 100191, ChinaSchool of Astronautics, Beihang University, Beijing 100191, ChinaSchool of Astronautics, Beihang University, Beijing 100191, ChinaAiming at the attack and defense game problem in the target-missile-defender three-body confrontation scenario, intelligent game strategies based on deep reinforcement learning are proposed, including an attack strategy applicable to attacking missiles and active defense strategy applicable to a target/defender. First, based on the classical three-body adversarial research, the reinforcement learning algorithm is introduced to improve the purposefulness of the algorithm training. The action spaces the reward and punishment conditions of both attack and defense confrontation are considered in the reward function design. Through the analysis of the sign of the action space and design of the reward function in the adversarial form, the combat requirements can be satisfied in both the missile and target/defender training. Then, a curriculum-based deep reinforcement learning algorithm is applied to train the agents and a convergent game strategy is obtained. The simulation results show that the attack strategy of the missile can maneuver according to the battlefield situation and can successfully hit the target after avoiding the defender. The active defense strategy enables the less capable target/defender to achieve the effect similar to a network adversarial attack on the missile agent, shielding targets from attack against missiles with superior maneuverability on the battlefield.https://www.mdpi.com/2226-4310/10/2/133target-missile-defender engagementthree-body gamecurriculum learningdeep reinforcement learningintelligent gameactive defense |
| spellingShingle | Xiaopeng Gong Wanchun Chen Zhongyuan Chen Intelligent Game Strategies in Target-Missile-Defender Engagement Using Curriculum-Based Deep Reinforcement Learning Aerospace target-missile-defender engagement three-body game curriculum learning deep reinforcement learning intelligent game active defense |
| title | Intelligent Game Strategies in Target-Missile-Defender Engagement Using Curriculum-Based Deep Reinforcement Learning |
| title_full | Intelligent Game Strategies in Target-Missile-Defender Engagement Using Curriculum-Based Deep Reinforcement Learning |
| title_fullStr | Intelligent Game Strategies in Target-Missile-Defender Engagement Using Curriculum-Based Deep Reinforcement Learning |
| title_full_unstemmed | Intelligent Game Strategies in Target-Missile-Defender Engagement Using Curriculum-Based Deep Reinforcement Learning |
| title_short | Intelligent Game Strategies in Target-Missile-Defender Engagement Using Curriculum-Based Deep Reinforcement Learning |
| title_sort | intelligent game strategies in target missile defender engagement using curriculum based deep reinforcement learning |
| topic | target-missile-defender engagement three-body game curriculum learning deep reinforcement learning intelligent game active defense |
| url | https://www.mdpi.com/2226-4310/10/2/133 |
| work_keys_str_mv | AT xiaopenggong intelligentgamestrategiesintargetmissiledefenderengagementusingcurriculumbaseddeepreinforcementlearning AT wanchunchen intelligentgamestrategiesintargetmissiledefenderengagementusingcurriculumbaseddeepreinforcementlearning AT zhongyuanchen intelligentgamestrategiesintargetmissiledefenderengagementusingcurriculumbaseddeepreinforcementlearning |