# 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.

```yaml
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.

```yaml
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.

```python
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.

```yaml
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.