How does Memoization Policy with max history argument chooses its next action? Does it need to be up to max histroy identical to stories or just a sub part? I recognize that in my case MemoizationPolicy picts wrong next action although this is not part of story. When using max history = 2, in my case just the prev action might be encountered in stories.

I’m not sure i entirely understand your question, but if a history of 2 (or whatever your max history value is) is available, it takes that amount of history into consideration

from what i noticed is one full story. * welcome - utter_welcome * greet - utter_greet if your max history is 2, this story needs to have an exact match. that’s my presumption

Must this be part of any story or one whole story itself with an ID?

@datistiquo Having a question regarding this as well. And maybe we could collaboratively work on a more extensive documentation of the entire policy part. To my understanding after reading the featurizer and policies docs, it sounds to me like every single event e.g. running a bot action, receiving a user message, setting slots creates a new state. However, the memoization policy only takes into account the last max_history states at prediction time. An example: Let’s take the following story * welcome - utter_welcome * greet - utter_greet - utter_how_can_i_help My tracker event history overall shows 11 events for this example: (only showing event types for length reasons) 1. user (user's welcome utterance) 2. action (utter_welcome action) 3. bot (bot's welcome utterance) 4. user (user's greet utterance) 5. action (utter_greet action) 6. bot (bot's greet utterance) 7. action (utter_how_can_i_help action) 8. bot (bot's how_can_i_help utterance) 9. action (listen) However, we only care about the last (let’s say 3) states at prediction, e.g. when predicting the action after utter_greet the featurized states will look something like: [ {'prev_action_utter_welcome': 1.0, 'intent_welcome': 1.0}, # oldest featurized prediction state {'prev_action_listen': 1.0, 'intent_greet': 1.0}, {'prev_utter_greet': 1.0, 'intent_greet': 1.0} # last featurized prediction state ] These are essentially pairs of (last_user_message, last_bot_action) and could be read like: Initially, I responded with utter_welcome to user’s intent_welcome (beginning of conversation) Then, I listened and and received intent_greet Just now, I responded with utter_greet to user’s intent_greet Additionally, the set slots and entities are also included and in these states and considered during prediction. So for this example, you’d already need a max_history=3 even though there are just 2 turns. Is this correct so far @akelad @souvikg10? However, I’m still unclear about a few other memoization related things: Augmentation Factor I see that data is augmented generally before training and seems to not be treated differently depending on the policy that is being trained. If a story is only 3 prediction events long, but max_history is 5, then it will only be memorized if I randomly walked any of the augmented paths that include my story, correct? This would essentially mean my augmentation factor should be so large, that almost any combination of story appears in the training data at least once. Shouldn’t I use no augmentation for Memoization though? Which would cause other ML policies to generalize worse though, right? AugmentedMemoizationPolicy Shouldn’t I almost always use this one instead? Since memoization takes slots into account, I typically don’t want any previously set slots to mess up my memoization, do I? Maybe I’m getting it wrong, but let’s say I have this story: * thanks - utter_thanks But if the first thing my bot does is ask the user for its name and store it in a slot, then my training story (with slot name = None) and the real context (name = some name) will always differ, causing the memoization to never match this story, correct? Inconsistent behavior due to max_history If my max_history is small, what happens if the same last events are followed by multiple, different events? E.g. I could have * intent1 - utter2 * intent3 - utter4 and * intent5 - utter2 * intent3 - utter6 If max_history is so short that it only spans across utter2 & intent3, what would it do? Not predict anything? Predict utter4 or utter6 randomly? Thanks a lot @akelad! Sorry for this very long post. Just saw many questions around this topic on the forum and lots of unclarity that I thought would be useful to address. Hope you’re the right person for this.

@smn-snkl I have provided a detailed solution for this, Kindly have a look. [image] [Solved]Predicted Action not following the story Rasa Open Source I have two stories which shares some of the intents. The action is not being executed as per both stories. The story is getting stuck at following point story 1(with intent 1) Inform -slot{‘id’=100} -action_validate story 2 (with intent2) *Inform -slot{‘id’=100} -action_register It is executing action_validate in place of action_execute. I have set max_history in memoization policy to 10, augmentation factor to 0. But the prediction for next action is not coming correct. I checked in deb…

@ashukrishna100 : Thanks for sharing your insights. I was, however, rather looking for the algorithmic explanation so I can make sure I choose and configure my policies appropriately.

@smn-snkl That are questions I asked myself too in the past. Like: Need the whole story block matches the story or just a part of it to be used by MemoPolicy? I think a state used for prediction is this featurized tracker state at one time which consists of intents, last actions, entities…And max_history means you have max_history of them using for prediction.

1.) memoization policy- this policy is used to remember the events as per story. 2.)keras policy: this policy is used to predict next action if the user asks something different from stories. However,tracker depends on max_history parameters in case path of two/more stories are very similar. If we pass max_history parameter to memoization policy it compares the user path with story path and if it is same,predict the next action correctly. If we pass max_history parameter to keras policy,it tunes our model for unknown events/not exactly same as stories. Augmentation factor stitches stories and then the policies(keras and memoization) act on those stitched stories. You can find those sticthed stories in models/dialogue.

[ {‘prev_action_utter_welcome’: 1.0, ‘intent_welcome’: 1.0}, # oldest featurized prediction state {‘prev_action_listen’: 1.0, ‘intent_greet’: 1.0}, {‘prev_utter_greet’: 1.0, ‘intent_greet’: 1.0} # last featurized prediction state ] Your list of tracker contains 3 elements i.e. your max history is 3, if u pass max history 30 the list will contain 30 elements

Memoization Policy with max history

Rasa Open Source

datistiquo (Datisto) October 26, 2018, 8:10am 3

Yea so the last 2 states have to coincide with one part of one of the stories or with one whole story?

Topic		Replies	Views
[Solved]Predicted Action not following the story Rasa Open Source	18	9751	April 4, 2022
How and when is MemoizationPolicy used? Rasa Open Source	6	1892	July 29, 2020
Need some help in understanding/using keras and memoization policy, in my case it needs to follow exact story path no deviation Rasa Open Source	3	954	June 21, 2019
Why MemoizationPolicy doesn't always work? Rasa Open Source	2	650	October 1, 2019
Memoization Policy after Form Policy "Fail" Rasa Open Source	10	839	May 12, 2020

Memoization Policy with max history

Related topics