Ship global path planning based on improved DQN algorithm

网络参数	数值
经验池容量N	5 000
学习率$ \alpha $	0.000 1
折扣因子$ \gamma $	0.95
贪婪率$ \varepsilon $	0.05～0.95
批量大小$ {B_1} $	256
目标网络更新频率M	100
单轮最大步数$ {T_{\max }} $	500

Table 2. Experimental results comparison of the three algorithms
View table
View in Article
Table 2. Experimental results comparison of the three algorithms
算法路径长度拐点数量时间/s
A^* 59.76 16 5.2
DQN 59.18 8 4.4
改进DQN 58.60 6 4.2

Table 3. Experimental results comparison of the three algorithms in Scenario-1
View table
View in Article
Table 3. Experimental results comparison of the three algorithms in Scenario-1
算法路径长度拐点数量时间/s
A^* 30.90 5 3.5
DQN 30.90 5 2.2
改进DQN 30.31 3 2.2

Table 4. Experimental results comparison of the three algorithms in Scenario-2
View table
View in Article
Table 4. Experimental results comparison of the three algorithms in Scenario-2
算法路径长度拐点数量时间/s
A^* 41.21 17 4.3
DQN 42.04 10 3.1
改进DQN 41.21 10 3.0

Tools

Get Citation

Copy Citation Text

Wei GUAN, Sheng QU, Xianku ZHANG, Tongbo HU. Ship global path planning based on improved DQN algorithm[J]. Chinese Journal of Ship Research, 2025, 20(1): 107

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites