Skip to main content

Table 1 TD3 and DDPG training hyperparameters

From: Peer-to-peer energy trading optimization in energy communities using multi-agent deep reinforcement learning

Hyperparameter

Value

Train batch size

100

Tau (Ï„)

0.005

Gamma (γ)

0.99

Critic learning rate

0.001

Actor learning rate

0.001

Policy delay

2

Policy noise

0.2

Noise clip

0.5