Portfolio-Management-ActorCriticRL
Portfolio-Management-ActorCriticRL copied to clipboard
DDPG - Noise added during test phase
Hello again,
I see that noise is added to predicted action (mu) even during test/eval phase. As noise is used for exploration, shouldn't it be used only during training phase ?
Thanks
It’s because exploration is needed for training RL agents. I don't remember the exact implementation, but I probably should have used a smaller noise for the testing phase.