Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ tags:
|
|
| 22 |

|
| 23 |
|
| 24 |
|
| 25 |
-
**
|
| 26 |
|
| 27 |
**Instead of training an additional reward model that is likely to be gamed, we directly train the model on the social games!** 🕹️ 🎲 🎮
|
| 28 |
|
|
|
|
| 22 |

|
| 23 |
|
| 24 |
|
| 25 |
+
**Efficient, Effective, and Stable alternative of RLHF!**
|
| 26 |
|
| 27 |
**Instead of training an additional reward model that is likely to be gamed, we directly train the model on the social games!** 🕹️ 🎲 🎮
|
| 28 |
|