Energy Management Model of Intelligent Park Based on Improved Depth Deterministic Gradient Strategy Algorithm

Table 1

Final reward of each agent in different cases.

Option	Random	Perceptual learning ratio	Experience pools	Reward value	Training time (h)
1	×	1	1	0.162	21.6
2	√	1	1	0.194	19.54
3	√	30 : 1	1	0.226	13.65
4	√	30 : 1	2	0.23	12.16