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 9 各算法在2种目标运动模式下的性能比较 |
| Fig.9 Performance comparison of various algorithms under two target motion modes |
|
|