Policies

Warning: This document is for an old version of Rasa. The latest version is 1.10.26.

Configuring Policies

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

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.

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.

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.

TED Policy

The Transformer Embedding Dialogue (TED) Policy is a model for dialogue management.

Mapping Policy

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

Memoization Policy

The MemoizationPolicy just memorizes the conversations in your training data.

Augmented Memoization Policy

The AugmentedMemoizationPolicy remembers examples from training stories for up to max_history turns.

Fallback Policy

The FallbackPolicy invokes a fallback action if certain confidence thresholds are not met.

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 manages form filling.

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