Human Feedback
material
ID: humanfeedback
Outgoing Relationships
| Relationship | Target Entity | Type | Actions |
|---|---|---|---|
| informs | Supervised Learning | method | View |
| informs | Reward based learning | method | View |
| informs | Reward Function | method | View |
| informs | Rejection sampling | method | View |
| informs | Model guiding | method | View |
| improves | NLPTasks | task | View |