ray.rllib.utils.exploration.parameter_noise.ParameterNoise.__init__#

ParameterNoise.__init__(action_space, *, framework: str, policy_config: dict, model: ModelV2, initial_stddev: float = 1.0, random_timesteps: int = 10000, sub_exploration: dict | None = None, **kwargs)[source]#

Initializes a ParameterNoise Exploration object.

Parameters:

  • initial_stddev – The initial stddev to use for the noise.

  • random_timesteps – The number of timesteps to act completely randomly (see [1]).

  • sub_exploration – Optional sub-exploration config. None for auto-detection/setup.