Action Noise¶
- class stable_baselines3.common.noise.NormalActionNoise(mean, sigma)[source]¶
A Gaussian action noise
- Parameters:
mean (
ndarray
) – the mean value of the noisesigma (
ndarray
) – the scale of the noise (std here)
- class stable_baselines3.common.noise.OrnsteinUhlenbeckActionNoise(mean, sigma, theta=0.15, dt=0.01, initial_noise=None)[source]¶
An Ornstein Uhlenbeck action noise, this is designed to approximate Brownian motion with friction.
Based on http://math.stackexchange.com/questions/1287634/implementing-ornstein-uhlenbeck-in-matlab
- Parameters:
mean (
ndarray
) – the mean of the noisesigma (
ndarray
) – the scale of the noisetheta (
float
) – the rate of mean reversiondt (
float
) – the timestep for the noiseinitial_noise (
Optional
[ndarray
]) – the initial value for the noise output, (if None: 0)
- class stable_baselines3.common.noise.VectorizedActionNoise(base_noise, n_envs)[source]¶
A Vectorized action noise for parallel environments.
- Parameters:
base_noise (
ActionNoise
) – ActionNoise The noise generator to usen_envs (
int
) – The number of parallel environments