Policies

Overview

These docs are for version 1.x of Rasa Open Source.

Introduction

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

Configuring Policies

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.

max_history: 5

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. You can alter this behavior with the --augmentation flag.

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 following is a basic structure of the model.

def model_architecture(self, input_shape, output_shape):
    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]))

model.compile(loss="categorical_crossentropy", optimizer="rmsprop", metrics=["accuracy"])

return model

Policies Definitions

Memoization Policy

The MemoizationPolicy just memorizes the conversations in your training data.

Augmented Memoization Policy

Remembers examples from training stories for up to max_history turns.

Fallback Policy

Invokes a fallback action if intent recognition confidence is below a specified threshold.

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

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.