PPO Agent playing SnowballTarget
This is a trained model of a PPO agent playing SnowballTarget using Unity ML-Agents and the Deep RL Course Unit 5.
Evaluation Results
- Mean Reward: 25.00 +/- 2.00
- Threshold: -100.0 (Passed)
Usage
Load SnowballTarget.onnx into the Unity ML-Agents environment.
- Downloads last month
- 11
Evaluation results
- mean_reward on ML-Agents-SnowballTargetself-reported25.00 +/- 2.00