tf_agents.policies.random_py_policy.RandomPyPolicy

Returns random samples of the given action_spec.

Inherits From: PyPolicy

tf_agents.policies.random_py_policy.RandomPyPolicy(
    time_step_spec: tf_agents.trajectories.TimeStep,
    action_spec: tf_agents.typing.types.NestedArraySpec,
    policy_state_spec: tf_agents.typing.types.NestedArraySpec = (),
    info_spec: tf_agents.typing.types.NestedArraySpec = (),
    seed: Optional[types.Seed] = None,
    outer_dims: Optional[Sequence[int]] = None,
    observation_and_action_constraint_splitter: Optional[types.Splitter] = None
)

Used in the notebooks

Used in the tutorials

time_step_spec Reference time_step_spec. If not None and outer_dims is not provided this is used to infer the outer_dims required for the given time_step when action is called.
action_spec A nest of BoundedArraySpec representing the actions to sample from.
policy_state_spec Nest of tf.TypeSpec representing the data in the policy state field.
info_spec Nest of tf.TypeSpec representing the data in the policy info field.
seed Optional seed used to instantiate a random number generator.
outer_dims An optional list/tuple specifying outer dimensions to add to the spec shape before sampling. If unspecified the outer_dims are derived from the outer_dims in the given observation when action is called.
observation_and_action_constraint_splitter A function used to process observations with action constraints. These constraints can indicate, for example, a mask of valid/invalid actions for a given state of the environment. The function takes in a full observation and returns a tuple consisting of 1) the part of the observation intended as input to the network and 2) the constraint. An example observation_and_action_constraint_splitter could be as simple as: def observation_and_action_constraint_splitter(observation): return observation['network_input'], observation['constraint'] Note: when using observation_and_action_constraint_splitter, make sure the provided q_network is compatible with the network-specific half of the output of the observation_and_action_constraint_splitter. In particular, observation_and_action_constraint_splitter will be called on the observation before passing to the network. If observation_and_action_constraint_splitter is None, action constraints are not applied.

action_spec Describes the ArraySpecs of the np.Array returned by action().

action can be a single np.Array, or a nested dict, list or tuple of np.Array.

collect_data_spec Describes the data collected when using this policy with an environment.
info_spec Describes the Arrays emitted as info by action().
observation_and_action_constraint_splitter

policy_state_spec Describes the arrays expected by functions with policy_state as input.
policy_step_spec Describes the output of action().
time_step_spec Describes the TimeStep np.Arrays expected by action(time_step).
trajectory_spec Describes the data collected when using this policy with an environment.

Methods

action

View source

action(
    time_step: tf_agents.trajectories.TimeStep,
    policy_state: tf_agents.typing.types.NestedArray = (),
    seed: Optional[types.Seed] = None
) -> tf_agents.trajectories.PolicyStep

Generates next action given the time_step and policy_state.

Args
time_step A TimeStep tuple corresponding to time_step_spec().
policy_state An optional previous policy_state.
seed Seed to use if action uses sampling (optional).

Returns
A PolicyStep named tuple containing: action: A nest of action Arrays matching the action_spec(). state: A nest of policy states to be fed into the next call to action. info: Optional side information such as action log probabilities.

get_initial_state

View source

get_initial_state(
    batch_size: Optional[int] = None
) -> tf_agents.typing.types.NestedArray

Returns an initial state usable by the policy.

Args
batch_size An optional batch size.

Returns
An initial policy state.