基于自适应课程强化学习的多无人艇对抗围捕决策
Decision-making for multi-USV adversarial encirclement based on adaptive curriculum reinforcement learning
基于自适应课程强化学习的多无人艇对抗围捕决策 |
| 陈浪,刘增力,赵宣植 |
|
Decision-making for multi-USV adversarial encirclement based on adaptive curriculum reinforcement learning |
| Lang CHEN,Zengli LIU,Xuanzhi ZHAO |
| 图 5 自适应课程学习-多智能体近端策略优化算法训练架构 |
| Fig.5 Training architecture of ACL-MAPPO algorithm |
|
|