Research on the Agricultural Machinery Path Tracking Method Based on Deep Reinforcement Learning

Table 2

I-DQN algorithm path tracking results.

	Target end	Path length (m)	Moving time (s)
1	(−1.13, 0.67)	1.41	7.73
2	(0.84, 1.04)	1.44	7.96
3	(−0.27, 0.34)	1.46	8.27
4	(−1.17, −0.96)	1.62	8.58
5	(0.86, 1.36)	1.69	9.10
6	(0.05, 1.66)	1.73	9.57
7	(−0.91, 1.41)	1.75	9.97
8	(−1.18, 1.33)	1.86	10.11
9	(−1.29, 1.50)	2.11	11.22
10	(1.44, 1.98)	—	—