Policies

Policies

Configuring Policies

The rasa.core.policies.Policy class decides which action to take at every step in the conversation.

There are different policies to choose from, and you can include multiple policies in a single rasa.core.agent.Agent.

Note: Per default a maximum of 10 next actions can be predicted by the agent after every user message. To update this value you can set the environment variable MAX_NUMBER_OF_PREDICTIONS to the desired number of maximum predictions.

Your project’s config.yml file takes a policies key which you can use to customize the policies your assistant uses.

policies:
  - name: "KerasPolicy"
    featurizer:
    - name: MaxHistoryTrackerFeaturizer
      max_history: 5
      state_featurizer:
        - name: BinarySingleStateFeaturizer
  - name: "MemoizationPolicy"
    max_history: 5
  - name: "FallbackPolicy"
    nlu_threshold: 0.4
    core_threshold: 0.3
    fallback_action_name: "my_fallback_action"
  - name: "path.to.your.policy.class"
    arg1: "..."

Max History

One important hyperparameter for Rasa Core policies is the max_history. This controls how much dialogue history the model looks at to decide which action to take next.

You can set the max_history by passing it to your policy’s Featurizer in the policy configuration yaml file.

Note: Only the MaxHistoryTrackerFeaturizer uses a max history, whereas the FullDialogueTrackerFeaturizer always looks at the full conversation history.

As an example, let’s say you have an out_of_scope intent which describes off-topic user messages.

* out_of_scope
   - utter_default
* out_of_scope
   - utter_default
* out_of_scope
   - utter_help_message

For Rasa Core to learn this pattern, the max_history has to be at least 4.

Data Augmentation

When you train a model, by default Rasa Core will create longer stories by randomly gluing together the ones in your stories files.

To alter this behavior with the --augmentation flag, use the augmentation_factor. The augmentation_factor determines how many augmented stories are subsampled during training.

--augmentation 0

Disables all augmentation behavior.

Action Selection

At every turn, each policy defined in your configuration will predict a next action with a certain confidence level.

In the case that two policies predict with equal confidence, the priority of the policies is considered. Rasa policies have default priorities that are set to ensure the expected outcome in the case of a tie.

Keras Policy

The KerasPolicy uses a neural network implemented in Keras to select the next action.

def model_architecture(self, input_shape: Tuple[int, int], output_shape: Tuple[int, Optional[int]]) -> tf.keras.models.Sequential:
    """Build a keras model and return a compiled model."""
    from tensorflow.keras.models import Sequential
    from tensorflow.keras.layers import Masking, LSTM, Dense, TimeDistributed, Activation

# Build Model
    model = Sequential()
    model.add(Masking(mask_value=-1, input_shape=input_shape))
    model.add(LSTM(self.rnn_size, dropout=0.2))
    model.add(Dense(input_dim=self.rnn_size, units=output_shape[-1]))

Embedding Policy

Warning: EmbeddingPolicy was renamed to TEDPolicy. Please use TED Policy instead.

Mapping Policy

The MappingPolicy can be used to directly map intents to actions.

intents:
 - ask_is_bot:
     triggers: action_is_bot

Memoization Policy

The MemoizationPolicy just memorizes the conversations in your training data.

Fallback Policy

The FallbackPolicy invokes a fallback action if at least one of the following occurs:

  1. The intent recognition has a confidence below nlu_threshold.
  2. The highest ranked intent differs in confidence with the second highest ranked intent by less than ambiguity_threshold.
  3. None of the dialogue policies predict an action with confidence higher than core_threshold.

Configuration:

policies:
  - name: "FallbackPolicy"
    nlu_threshold: 0.3
    ambiguity_threshold: 0.1
    core_threshold: 0.3
    fallback_action_name: 'action_default_fallback'

Two-Stage Fallback Policy

The TwoStageFallbackPolicy handles low NLU confidence in multiple stages by trying to disambiguate the user input.