Fall back policy is not working

[ermarkar (Sunil Garg)]

I want to implement two stage fallback policy, and i followed this aritcle

Fallback and Human Handoff

here is config.yml

language: en
pipeline:
  # other policies
  - name: DIETClassifier
    epochs: 100
    entity_recognition: False
  - name: ResponseSelector
    epochs: 100
  - name: FallbackClassifier
    threshold: 0.7
policies:
  - name: TEDPolicy
    max_history: 10
    epochs: 20
  - name: AugmentedMemoizationPolicy
    max_history: 6
  - name: RulePolicy

added rule in rules.yml - rule: Implementation of the Two-Stage-Fallback steps: - intent: nlu_fallback - action: action_two_stage_fallback - active_loop: action_two_stage_fallback

and response in domain.yml

responses:
  utter_ask_rephrase:
  - text: I'm sorry, I didn't quite understand that. Could you rephrase? 

and on intent confidence goodbye0.23 it is executing goodbye not the fallback policy.

Am i missing something?

[ermarkar (Sunil Garg)]

I need to mention few params for RulePolicy

- name: RulePolicy
    core_fallback_threshold: 0.3
    core_fallback_action_name: "action_default_fallback"
    enable_fallback_prediction: True

further rasa will use raw intent names while guessing the possible most likely intent to user.

to solve that

rasa nlu fallback is returning intent instead of question

[karan (Nishakaran Pushpa Rajah)]

@ermarkar

AugmentedMemoizationPolicy

The bot understands and picks up the intent after the ask for affirmation, but there is no action after intent detected. Did you face similar issue?

I am using Rasa 3.1

[Prakashram27 (Prakash Ramu)]

Hey hi karan, I am facing following problem, please let me how to solve this.