garage.np.policies

Policies which use NumPy as a numerical backend.

class FixedPolicy(env_spec, scripted_actions, agent_infos=None)

Bases: garage.np.policies.policy.Policy

Policy that performs a fixed sequence of actions.

Parameters:

• env_spec (garage.envs.env_spec.EnvSpec) – Environment specification.
• scripted_actions (list[np.ndarray] or np.ndarray) – Sequence of actions to perform.
• agent_infos (list[dict[str, np.ndarray]] or None) – Sequence of agent_infos to produce.

env_spec

Policy environment specification.

Returns:Environment specification. Return type:garage.EnvSpec

name

Name of policy.

Returns:Name of policy Return type:str

observation_space

Observation space.

Returns:The observation space of the environment. Return type:akro.Space

action_space

Action space.

Returns:The action space of the environment. Return type:akro.Space

reset(self, do_resets=None)

Reset policy.

Parameters:do_resets (None or list[bool]) – Vectorized policy states to reset. Raises:ValueError – If do_resets has length greater than 1.

set_param_values(self, params)

Set param values of policy.

Parameters:params (object) – Ignored.

get_param_values(self)

Return policy params (there are none).

Returns:Empty tuple. Return type:tuple

get_action(self, observation)

Get next action.

Parameters:observation (np.ndarray) – Ignored. Raises:ValueError – If policy is currently vectorized (reset was called with more than one done value). Returns:

The action and agent_info

for this time step.

Return type:tuple[np.ndarray, dict[str, np.ndarray]]

get_actions(self, observations)

Get next action.

Parameters:observations (np.ndarray) – Ignored. Raises:ValueError – If observations has length greater than 1. Returns:

The action and agent_info

for this time step.

Return type:tuple[np.ndarray, dict[str, np.ndarray]]

class Policy

Bases: abc.ABC

Base class for policies based on numpy.

name

Name of policy.

Returns:Name of policy Return type:str

env_spec

Policy environment specification.

Returns:Environment specification. Return type:garage.EnvSpec

observation_space

Observation space.

Returns:The observation space of the environment. Return type:akro.Space

action_space

Action space.

Returns:The action space of the environment. Return type:akro.Space

get_action(self, observation)

Get action sampled from the policy.

Parameters:observation (np.ndarray) – Observation from the environment. Returns:

Actions and extra agent

infos.

Return type:Tuple[np.ndarray, dict[str,np.ndarray]]

get_actions(self, observations)

Get actions given observations.

Parameters:observations (torch.Tensor) – Observations from the environment. Returns:

Actions and extra agent

infos.

Return type:Tuple[np.ndarray, dict[str,np.ndarray]]

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.

class ScriptedPolicy(scripted_actions, agent_env_infos=None)

Bases: garage.np.policies.policy.Policy

Simulates a garage policy object.

Parameters:

• scripted_actions (list or dictionary) – data structure indexed by observation, returns a corresponding action
• agent_env_infos (list or dictionary) – data structure indexed by observation, returns a corresponding agent_env_info

name

Name of policy.

Returns:Name of policy Return type:str

env_spec

Policy environment specification.

Returns:Environment specification. Return type:garage.EnvSpec

observation_space

Observation space.

Returns:The observation space of the environment. Return type:akro.Space

action_space

Action space.

Returns:The action space of the environment. Return type:akro.Space

set_param_values(self, params)

Set param values.

Parameters:params (np.ndarray) – A numpy array of parameter values.

get_param_values(self)

Get param values.

Returns:

Values of the parameters evaluated in

the current session

Return type:np.ndarray

get_action(self, observation)

Return a single action.

Parameters:observation (numpy.ndarray) – Observations. Returns:Action given input observation. dict[dict]: Agent infos indexed by observation. Return type:int

get_actions(self, observations)

Return multiple actions.

Parameters:observations (numpy.ndarray) – Observations. Returns:Actions given input observations. dict[dict]: Agent info indexed by observation. Return type:list[int]

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.