mukie commited on
Commit
388aba5
·
verified ·
1 Parent(s): e02f066

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -9,7 +9,7 @@ metrics:
9
  # OpenCausaLab/CauGym
10
 
11
  <!-- Provide a quick summary of what the model is/does. -->
12
- This model is specialized for causal inference.
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 |