Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ metrics:
|
|
| 9 |
# OpenCausaLab/CauGym
|
| 10 |
|
| 11 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 12 |
-
|
| 13 |
|
| 14 |
## Model Details
|
| 15 |
|
|
@@ -25,8 +25,10 @@ This model is specialized for causal inference.
|
|
| 25 |
- **Repository:** https://github.com/OpenCausaLab/CauGym
|
| 26 |
- **Paper :** https://www.arxiv.org/abs/2602.06337
|
| 27 |
|
|
|
|
| 28 |
### Evaluation
|
| 29 |
|
|
|
|
| 30 |
| Benchmark | ATE | CDE | ETT | NDE | NIE | PN | PS |
|
| 31 |
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
|
| 32 |
| **CALM** | 0.990 | 0.994 | 0.900 | 0.940 | 0.930 | 0.928 | 0.866 |
|
|
|
|
| 9 |
# OpenCausaLab/CauGym
|
| 10 |
|
| 11 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 12 |
+
CauGym model is a model trained via GRPO (Group Relative Policy Optimization) on VERL framework (https://github.com/verl-project/verl), and it is specialized for causal inference.
|
| 13 |
|
| 14 |
## Model Details
|
| 15 |
|
|
|
|
| 25 |
- **Repository:** https://github.com/OpenCausaLab/CauGym
|
| 26 |
- **Paper :** https://www.arxiv.org/abs/2602.06337
|
| 27 |
|
| 28 |
+
|
| 29 |
### Evaluation
|
| 30 |
|
| 31 |
+
We have evaluated this model on CALM benchmark and CauGym benchmark, and the evaluation metric is accuracy.
|
| 32 |
| Benchmark | ATE | CDE | ETT | NDE | NIE | PN | PS |
|
| 33 |
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
|
| 34 |
| **CALM** | 0.990 | 0.994 | 0.900 | 0.940 | 0.930 | 0.928 | 0.866 |
|