tf_agents/bandits/policies/boltzmann_reward_prediction_policy.py [141:164]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    self._emit_policy_info = emit_policy_info
    predicted_rewards_mean = ()
    if policy_utilities.InfoFields.PREDICTED_REWARDS_MEAN in emit_policy_info:
      predicted_rewards_mean = tensor_spec.TensorSpec(
          [self._expected_num_actions])
    bandit_policy_type = ()
    if policy_utilities.InfoFields.BANDIT_POLICY_TYPE in emit_policy_info:
      bandit_policy_type = (
          policy_utilities.create_bandit_policy_type_tensor_spec(shape=[1]))
    if accepts_per_arm_features:
      # The features for the chosen arm is saved to policy_info.
      chosen_arm_features_info = (
          policy_utilities.create_chosen_arm_features_info_spec(
              time_step_spec.observation))
      info_spec = policy_utilities.PerArmPolicyInfo(
          predicted_rewards_mean=predicted_rewards_mean,
          bandit_policy_type=bandit_policy_type,
          chosen_arm_features=chosen_arm_features_info)
    else:
      info_spec = policy_utilities.PolicyInfo(
          predicted_rewards_mean=predicted_rewards_mean,
          bandit_policy_type=bandit_policy_type)

    self._accepts_per_arm_features = accepts_per_arm_features
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tf_agents/bandits/policies/greedy_reward_prediction_policy.py [105:128]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    self._emit_policy_info = emit_policy_info
    predicted_rewards_mean = ()
    if policy_utilities.InfoFields.PREDICTED_REWARDS_MEAN in emit_policy_info:
      predicted_rewards_mean = tensor_spec.TensorSpec(
          [self._expected_num_actions])
    bandit_policy_type = ()
    if policy_utilities.InfoFields.BANDIT_POLICY_TYPE in emit_policy_info:
      bandit_policy_type = (
          policy_utilities.create_bandit_policy_type_tensor_spec(shape=[1]))
    if accepts_per_arm_features:
      # The features for the chosen arm is saved to policy_info.
      chosen_arm_features_info = (
          policy_utilities.create_chosen_arm_features_info_spec(
              time_step_spec.observation))
      info_spec = policy_utilities.PerArmPolicyInfo(
          predicted_rewards_mean=predicted_rewards_mean,
          bandit_policy_type=bandit_policy_type,
          chosen_arm_features=chosen_arm_features_info)
    else:
      info_spec = policy_utilities.PolicyInfo(
          predicted_rewards_mean=predicted_rewards_mean,
          bandit_policy_type=bandit_policy_type)

    self._accepts_per_arm_features = accepts_per_arm_features
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -