Niladri Das commited on
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -8,6 +8,10 @@ This model provides a solution to the CartPole-v1 environment using CMA-ES (Cova
|
|
| 8 |
achieving perfect performance with a simple linear policy. The implementation demonstrates how evolutionary strategies can
|
| 9 |
effectively solve classic control problems with minimal architecture complexity.
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
## Model Details
|
| 12 |
|
| 13 |
### Model Description
|
|
@@ -27,7 +31,6 @@ This is a linear policy model for the CartPole-v1 environment that:
|
|
| 27 |
### Model Sources
|
| 28 |
|
| 29 |
- **Repository:** https://huggingface.co/bniladridas/cartpole-cmaes
|
| 30 |
-
- **Demo:** https://huggingface.co/spaces/bniladridas/cartpole-cmaes-demo
|
| 31 |
|
| 32 |
## Uses
|
| 33 |
|
|
|
|
| 8 |
achieving perfect performance with a simple linear policy. The implementation demonstrates how evolutionary strategies can
|
| 9 |
effectively solve classic control problems with minimal architecture complexity.
|
| 10 |
|
| 11 |
+
### Training Convergence
|
| 12 |
+

|
| 13 |
+
*Figure: Training convergence showing the mean fitness (episode length) across generations. The model achieves optimal performance (500 steps) within 3 generations.*
|
| 14 |
+
|
| 15 |
## Model Details
|
| 16 |
|
| 17 |
### Model Description
|
|
|
|
| 31 |
### Model Sources
|
| 32 |
|
| 33 |
- **Repository:** https://huggingface.co/bniladridas/cartpole-cmaes
|
|
|
|
| 34 |
|
| 35 |
## Uses
|
| 36 |
|