Intercept Guidance of Maneuvering Targets with Deep Reinforcement Learning

Table 2

Hyperparameters for TD3 algorithm.

Parameter	Value
Number of hidden layers	2
BATCH_SIZE	32
Replay buffer size	50000
Actor learning rate	10^-5
Critic learning rate
Policy noise	0.2
Noise bound	0.5
Soft update factor	0.01
Discounting factor γ	0.95
Delay steps	5
Gradient optimizer	Adam