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. See Featurization of Conversations for details.

Example

# Rasa conversation pattern
* out_of_scope
   - utter_default
* out_of_scope
   - utter_default
* out_of_scope
   - utter_help_message

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.

# thanks
* thankyou
   - utter_youarewelcome

# bye
* goodbye
   - utter_goodbye

Action Selection

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

Keras Policy

The KerasPolicy uses a neural network implemented in Keras to select the next action. The default architecture is based on an LSTM, but you can override the KerasPolicy.model_architecture method to implement your own architecture.

def model_architecture(self, input_shape: Tuple[int, int], output_shape: Tuple[int, Optional[int]]) -> tf.keras.models.Sequential:
    # Build Keras Model
    model = Sequential()
    # Add layers
    # Return compiled model
    return model

Action Selection Details

The bot’s next action is then decided by the policy that predicts with the highest confidence.

Fallback Policy

The FallbackPolicy invokes a fallback action if a specific condition 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 Example

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.

Form Policy

The FormPolicy is an extension of the MemoizationPolicy which handles the filling of forms. Once a FormAction is called, the FormPolicy will continually predict the FormAction until all required slots in the form are filled.

👋 I can help you get started with Rasa and answer your technical questions.