ray.rllib.utils.exploration.gaussian_noise.GaussianNoise.__init__#

GaussianNoise.__init__(action_space: gymnasium.spaces.Space, *, framework: str, model: ModelV2, random_timesteps: int = 1000, stddev: float = 0.1, initial_scale: float = 1.0, final_scale: float = 0.02, scale_timesteps: int = 10000, scale_schedule: Schedule | None = None, **kwargs)[source]#

Initializes a GaussianNoise instance.

Parameters:

  • random_timesteps – The number of timesteps for which to act completely randomly. Only after this number of timesteps, the self.scale annealing process will start (see below).

  • stddev – The stddev (sigma) to use for the Gaussian noise to be added to the actions.

  • initial_scale – The initial scaling weight to multiply the noise with.

  • final_scale – The final scaling weight to multiply the noise with.

  • scale_timesteps – The timesteps over which to linearly anneal the scaling factor (after(!) having used random actions for random_timesteps steps).

  • scale_schedule – An optional Schedule object to use (instead of constructing one from the given parameters).