tf_agents/bandits/policies/greedy_multi_objective_neural_policy.py [85:147]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
      emit_policy_info: Tuple[Text, ...] = (),
      name: Optional[Text] = None):
    """Builds a GreedyMultiObjectiveNeuralPolicy based on multiple networks.

    This policy takes an iterable of `tf_agents.Network`, each responsible for
    predicting a specific objective, along with a `Scalarizer` object to
    generate an action by maximizing the scalarized objective, i.e., the output
    of the `Scalarizer` applied to the multiple predicted objectives by the
    networks.

    Args:
      time_step_spec: A `TimeStep` spec of the expected time_steps.
      action_spec: A nest of `BoundedTensorSpec` representing the actions.
      scalarizer: A
       `tf_agents.bandits.multi_objective.multi_objective_scalarizer.Scalarizer`
        object that implements scalarization of multiple objectives into a
        single scalar reward.
      objective_networks: A Sequence of `tf_agents.network.Network` objects to
        be used by the policy. Each network will be called with
        call(observation, step_type) and is expected to provide a prediction for
        a specific objective for all actions.
      observation_and_action_constraint_splitter: A function used for masking
        valid/invalid actions with each 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
        mask.  The mask should be a 0-1 `Tensor` of shape `[batch_size,
        num_actions]`. This function should also work with a `TensorSpec` as
        input, and should output `TensorSpec` objects for the observation and
        mask.
      accepts_per_arm_features: (bool) Whether the policy accepts per-arm
        features.
      emit_policy_info: (tuple of strings) what side information we want to get
        as part of the policy info. Allowed values can be found in
        `policy_utilities.PolicyInfo`.
      name: The name of this policy. All variables in this module will fall
        under that name. Defaults to the class name.

    Raises:
      NotImplementedError: If `action_spec` contains more than one
        `BoundedTensorSpec` or the `BoundedTensorSpec` is not valid.
      NotImplementedError: If `action_spec` is not a `BoundedTensorSpec` of type
        int32 and shape ().
      ValueError: If `objective_networks` has fewer than two networks.
      ValueError: If `accepts_per_arm_features` is true but `time_step_spec` is
        None.
    """
    policy_utilities.check_no_mask_with_arm_features(
        accepts_per_arm_features, observation_and_action_constraint_splitter)
    flat_action_spec = tf.nest.flatten(action_spec)
    if len(flat_action_spec) > 1:
      raise NotImplementedError(
          'action_spec can only contain a single BoundedTensorSpec.')

    action_spec = flat_action_spec[0]
    if (not tensor_spec.is_bounded(action_spec) or
        not tensor_spec.is_discrete(action_spec) or
        action_spec.shape.rank > 1 or
        action_spec.shape.num_elements() != 1):
      raise NotImplementedError(
          'action_spec must be a BoundedTensorSpec of type int32 and shape (). '
          'Found {}.'.format(action_spec))
    self._expected_num_actions = action_spec.maximum - action_spec.minimum + 1
    self._action_offset = action_spec.minimum
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tf_agents/bandits/policies/greedy_reward_prediction_policy.py [50:100]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
               emit_policy_info: Tuple[Text, ...] = (),
               name: Optional[Text] = None):
    """Builds a GreedyRewardPredictionPolicy given a reward tf_agents.Network.

    This policy takes a tf_agents.Network predicting rewards and generates the
    action corresponding to the largest predicted reward.

    Args:
      time_step_spec: A `TimeStep` spec of the expected time_steps.
      action_spec: A nest of BoundedTensorSpec representing the actions.
      reward_network: An instance of a `tf_agents.network.Network`,
        callable via `network(observation, step_type) -> (output, final_state)`.
      observation_and_action_constraint_splitter: A function used for masking
        valid/invalid actions with each 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
        mask.  The mask should be a 0-1 `Tensor` of shape
        `[batch_size, num_actions]`. This function should also work with a
        `TensorSpec` as input, and should output `TensorSpec` objects for the
        observation and mask.
      accepts_per_arm_features: (bool) Whether the policy accepts per-arm
        features.
      constraints: iterable of constraints objects that are instances of
        `tf_agents.bandits.agents.NeuralConstraint`.
      emit_policy_info: (tuple of strings) what side information we want to get
        as part of the policy info. Allowed values can be found in
        `policy_utilities.PolicyInfo`.
      name: The name of this policy. All variables in this module will fall
        under that name. Defaults to the class name.

    Raises:
      NotImplementedError: If `action_spec` contains more than one
        `BoundedTensorSpec` or the `BoundedTensorSpec` is not valid.
    """
    policy_utilities.check_no_mask_with_arm_features(
        accepts_per_arm_features, observation_and_action_constraint_splitter)
    flat_action_spec = tf.nest.flatten(action_spec)
    if len(flat_action_spec) > 1:
      raise NotImplementedError(
          'action_spec can only contain a single BoundedTensorSpec.')

    action_spec = flat_action_spec[0]
    if (not tensor_spec.is_bounded(action_spec) or
        not tensor_spec.is_discrete(action_spec) or
        action_spec.shape.rank > 1 or
        action_spec.shape.num_elements() != 1):
      raise NotImplementedError(
          'action_spec must be a BoundedTensorSpec of type int32 and shape (). '
          'Found {}.'.format(action_spec))
    self._expected_num_actions = action_spec.maximum - action_spec.minimum + 1
    self._action_offset = action_spec.minimum
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -