Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,48 @@
+---
+language: en
+license: mit
+library_name: stable-baselines3
+tags:
+- reinforcement-learning
+- stable-baselines3
+- gymnasium
+- maskable-ppo
+datasets:
+- custom-utdg-env
+metrics:
+- episode_reward
+---
+
+# UTDG Maskable PPO Policy
+
+This model is trained on the UTDG (Untitled Tower Defense Game) environment using Stable-Baselines3 MaskablePPO.
+
+## Model Details
+
+- **Algorithm**: MaskablePPO (Proximal Policy Optimization with invalid action masking)
+- **Framework**: Stable-Baselines3
+- **Environment**: Custom UTDG Gymnasium environment
+- **Task**: Tower defense game AI agent
+
+## Usage
+```python
+from huggingface_hub import hf_hub_download
+from sb3_contrib import MaskablePPO
+
+# Download the model
+model_path = hf_hub_download(
+    repo_id="chrisjcc/utdg-maskableppo-policy",
+    filename="maskableppo_utdg_policy.zip"
+)
+
+# Load the model
+model = MaskablePPO.load(model_path)
+
+# Use for inference
+# obs, info = env.reset()
+# action, _states = model.predict(obs, action_masks=info["action_mask"])
+```
+
+## Training
+
+The model was trained using reinforcement learning on the UTDG environment.