cjfrown/ppo-SnowballTarget

❄️ PPO Agent playing SnowballTarget

This Hugging Face Space hosts an interactive WebGL demo for the trained PPO Agent playing SnowballTarget.

🤖 Model Details

• —Model Repository: `cjfrown/ppo-SnowballTarget`
• —Framework: Unity ML-Agents Toolkit
• —Algorithm: Proximal Policy Optimization (PPO)
• —Environment: SnowballTarget

🎮 How it Works

The Unity WebGL environment runs directly inside your browser. The trained PPO policy model (SnowballTarget.onnx) guides the agent to target and hit objects with snowballs in the 3D environment.

• —Toggle Fullscreen: Click the fullscreen button in the bottom-right corner.
• —Model Card & Weights: Visit `cjfrown/ppo-SnowballTarget` to view model details, training configs, and raw ONNX weights.

Created as part of the Hugging Face Deep RL Course.