garage.np.exploration_strategies.gaussian_strategy module

Gaussian exploration strategy.

class GaussianStrategy(env_spec, max_sigma=1.0, min_sigma=0.1, decay_period=1000000)[source]

Bases: garage.np.exploration_strategies.base.ExplorationStrategy

Add Gaussian noise to the action taken by the deterministic policy.

get_action(iteration, observation, policy, **kwargs)[source]

Get action from this policy for the input observation.

Parameters:
  • iteration (int) – Iteration.
  • observation (numpy.ndarray) – Observation from the environment.
  • policy (garage.tf.policies.base.Policy) – Policy network to predict action based on the observation.
Returns:

optimal action from this policy. agent_info(dict): Agent information.
Return type:

opt_action(numpy.ndarray)
get_actions(iteration, observations, policy, **kwargs)[source]

Get actions from this policy for the input observation.

Parameters:
  • iteration (int) – Iteration.
  • observatioan (list) – Observationa from the environment.
  • policy (garage.tf.policies.base.Policy) – Policy network to predict action based on the observation.
Returns:

optimal actions from this policy. agent_infos(dict): Agent information.
Return type:

opt_actions(numpy.ndarray)