Network Architecture for Optimizing Deep Deterministic Policy Gradient Algorithms

Table 1

Mujoco environment model hyperparameters.

Order	Parameter	Value
1	Decay rate	0.9
2	Actor net learning rate	0.0001
3	Critic net learning rate	0.0001
4	Neuron number in 1^st layer	400
5	Neuron number in 2^nd layer	300
6	Experience pool volume	100000
7	Batch data size	256
8	Soft update coefficient	0.01
9	Action reward discount rate	0.99
10	Critic net output distribution low limit	−20
11	Target net parameters update round number	10