Offline Reinforcement Learning Methods
Direct Preference Optimization
Introduced by Rafailov et al. in Direct Preference Optimization: Your Language Model is Secretly a Reward ModelPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Language Modelling | 51 | 18.21% |
| Instruction Following | 19 | 6.79% |
| Large Language Model | 17 | 6.07% |
| Reinforcement Learning | 13 | 4.64% |
| Reinforcement Learning (RL) | 12 | 4.29% |
| Diversity | 10 | 3.57% |
| Mathematical Reasoning | 10 | 3.57% |
| Question Answering | 10 | 3.57% |
| Image Generation | 9 | 3.21% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
