bc_point

Example of using Behavioral Cloning.

class OptimalPolicy(env_spec, goal)

Bases: garage.torch.policies.Policy

Inheritance diagram of bc_point.OptimalPolicy

Optimal policy for PointEnv.

Parameters
  • env_spec (EnvSpec) – The environment spec.

  • goal (np.ndarray) – The goal location of the environment.

get_action(self, observation)

Get action given observation.

Parameters

observation (np.ndarray) – Observation from PointEnv. Should have length at least 2.

Returns

  • np.ndarray: Optimal action in the environment. Has length 2.

  • dict[str, np.ndarray]: Agent info (empty).

Return type

tuple

get_actions(self, observations)

Get actions given observations.

Parameters

observations (np.ndarray) – Observations from the environment. Has shape \((B, O)\), where \(B\) is the batch dimension and \(O\) is the observation dimensionality (at least 2).

Returns

  • np.ndarray: Batch of optimal actions.

    Has shape \((B, 2)\), where \(B\) is the batch dimension.

Optimal action in the environment. * dict[str, np.ndarray]: Agent info (empty).

Return type

tuple

get_param_values(self)

Get the parameters to the policy.

This method is included to ensure consistency with TF policies.

Returns

The parameters (in the form of the state dictionary).

Return type

dict

set_param_values(self, state_dict)

Set the parameters to the policy.

This method is included to ensure consistency with TF policies.

Parameters

state_dict (dict) – State dictionary.

property name(self)

Name of policy.

Returns

Name of policy

Return type

str

reset(self, do_resets=None)

Reset the policy.

This is effective only to recurrent policies.

do_resets is an array of boolean indicating which internal states to be reset. The length of do_resets should be equal to the length of inputs, i.e. batch size.

Parameters

do_resets (numpy.ndarray) – Bool array indicating which states to be reset.

property env_spec(self)

Policy environment specification.

Returns

Environment specification.

Return type

garage.EnvSpec

property observation_space(self)

Observation space.

Returns

The observation space of the environment.

Return type

akro.Space

property action_space(self)

Action space.

Returns

The action space of the environment.

Return type

akro.Space

bc_point(ctxt=None, loss='log_prob')

Run Behavioral Cloning on garage.envs.PointEnv.

Parameters
  • ctxt (ExperimentContext) – Provided by wrap_experiment.

  • loss (str) – Either ‘log_prob’ or ‘mse’