noise size equal to number of actions

[SarodYatawatta]

Youtube-Code-Repository/ReinforcementLearning/PolicyGradient/TD3/td3_torch.py

Line 163 in 733e452

mu_prime = mu + T.tensor(np.random.normal(scale=self.noise),

Instead of a scalar noise, should be a vector of number of actions size
mu_prime = mu + T.tensor(np.random.normal(scale=self.noise,size=(self.n_actions,)),

[philtabor]

We're allowed to add a scalar quantity to a vector. Is there a reason why each component of the mu tensor should have a different random number added to it?

[SarodYatawatta]

True, but by making mu tensor perturb by different random numbers, you can increase the exploration (as opposed to using the same random number)