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

class ray.rllib.utils.exploration.gaussian_noise.GaussianNoise(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]#

Bases: Exploration

An exploration that adds white noise to continuous actions.

If explore=True, returns actions plus scale (annealed over time) x Gaussian noise. Also, some completely random period is possible at the beginning.

If explore=False, returns the deterministic action.

Methods

`__init__`	Initializes a GaussianNoise instance.
`before_compute_actions`	Hook for preparations before policy.compute_actions() is called.
`get_exploration_optimizer`	May add optimizer(s) to the Policy's own `optimizers`.
`get_state`	Returns the current scale value.
`on_episode_end`	Handles necessary exploration logic at the end of an episode.
`on_episode_start`	Handles necessary exploration logic at the beginning of an episode.
`postprocess_trajectory`	Handles post-processing of done episode trajectories.