mnemostack_feedback
Record explicit feedback to improve stateful recall learning. Use signal='clicked' for inhibition-of-return and pass retriever labels as sources to update Q-learning weights.
Instructions
Record explicit feedback for stateful recall learning.
Use signal='clicked' to also record inhibition-of-return exposure. Pass retriever labels from mnemostack_search results as sources so Q-learning can update source weights.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| hit_id | Yes | ||
| signal | Yes | ||
| query | No | ||
| query_type | No | ||
| source | No | ||
| sources | No | ||
| reward | No |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||