ray.rllib.utils.exploration.stochastic_sampling.StochasticSampling.__init__#

StochasticSampling.__init__(action_space: <MagicMock name='mock.spaces.Space' id='140494124151808'>, *, framework: str, model: ray.rllib.models.modelv2.ModelV2, random_timesteps: int = 0, **kwargs)[source]#

Initializes a StochasticSampling Exploration object.

Parameters

  • action_space – The gym action space used by the environment.

  • framework – One of None, “tf”, “torch”.

  • model – The ModelV2 used by the owning Policy.

  • random_timesteps – The number of timesteps for which to act completely randomly. Only after this number of timesteps, actual samples will be drawn to get exploration actions.