Update README.md

README.md

@@ -1,37 +1,90 @@
----
-library_name: stable-baselines3
-tags:
-- FetchPickAndPlace-v4
-- deep-reinforcement-learning
-- reinforcement-learning
-- stable-baselines3
-model-index:
-- name: SAC
-  results:
-  - task:
-      type: reinforcement-learning
-      name: reinforcement-learning
-    dataset:
-      name: FetchPickAndPlace-v4
-      type: FetchPickAndPlace-v4
-    metrics:
-    - type: mean_reward
-      value: -9.70 +/- 4.17
-      name: mean_reward
-      verified: false
----
-
-# **SAC** Agent playing **FetchPickAndPlace-v4**
-This is a trained model of a **SAC** agent playing **FetchPickAndPlace-v4**
-using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
-
-## Usage (with Stable-baselines3)
-TODO: Add your code
-
-
-```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
-
-...
-```
+---
+library_name: stable-baselines3
+tags:
+- FetchPickAndPlace-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: FetchPickAndPlace-v4
+      type: FetchPickAndPlace-v4
+    metrics:
+    - type: mean_reward
+      value: -9.70 +/- 4.17
+      name: mean_reward
+      verified: false
+---
+
+# SAC Agent for FetchPickAndPlace-v4
+
+## Model Description
+
+This repository contains a Soft Actor-Critic (SAC) agent trained on the `FetchPickAndPlace-v4` environment using Hindsight Experience Replay (HER). The agent learns to pick and place objects in a simulated robotic environment.
+
+- **Algorithm:** Soft Actor-Critic (SAC)
+- **Replay Buffer:** Hindsight Experience Replay (HER)
+- **Environment:** FetchPickAndPlace-v4 (from gymnasium-robotics)
+- **Framework:** Stable Baselines3
+
+## Training Details
+
+- **Total Timesteps:** 500,000
+- **Dense Shaping:** Disabled
+- **Evaluation:** Success rate and mean reward measured every 2,000 steps
+- **Seed:** 42
+
+## Usage
+
+To load and use the model:
+
+```python
+from stable_baselines3 import SAC
+import gymnasium as gym
+import gymnasium_robotics
+
+env = gym.make("FetchPickAndPlace-v4", render_mode="rgb_array")
+model = SAC.load("path/to/sac-FetchPickAndPlace-v4.zip", env=env)
+
+obs, info = env.reset()
+done = False
+while not done:
+    action, _ = model.predict(obs, deterministic=True)
+    obs, reward, done, truncated, info = env.step(action)
+    env.render()
+```
+
+## Evaluation & Replay
+
+A replay video (`replay.mp4`) is included to visualize the agent's performance over two episodes.
+
+## Files
+
+- `sac-FetchPickAndPlace-v4.zip`: Trained SAC model
+- `replay.mp4`: Agent replay video
+- `README.md`: Model card
+
+## Citation
+
+If you use this model, please cite:
+
+```
+@misc{IntelliGrow_FetchPickAndPlace_SAC,
+  title={SAC Agent for FetchPickAndPlace-v4},
+  author={IntelliGrow},
+  year={2025},
+  howpublished={Hugging Face Hub},
+  url={https://huggingface.co/IntelliGrow/FetchPickAndPlace-v4}
+}
+```
+
+## License
+
+MIT License
+
+---