Hi, so I’m using memoization policy but after the first action, it fails to find the next action. As suggested in a previous post, I have set augmentation factor to 0, but to no avail.
When testing my bot, I literally took out the flattened version of stories.md that was dumped, and tried to follow it step by step. Still, the bot cannot find the action though I am reading from the generated stories (after checkpoint gluing).
Can anyone help here?
Augmentation factor will glue stories to create larger ones. setting it to 0 makes sure you only have stories that you have written in your training data. Did you try to adjust the max_history with the --history flag
Personally, i don’t like checkpoints as it doesn’t fully represent the training data. I use interactive learning to generate my stories full length stories.
@souvikg10 so much love for this comment. checkpoints can get very confusing so we like to avoid using them unless absolutely necessary
Checkpoint is not required if you write your stories well. I have written a detailed solution for this issue.