PPO Agent playing Pyramids
This is a trained model of a PPO agent playing Pyramids using Unity ML-Agents and the Deep RL Course Unit 5.
Evaluation Results
- Mean Reward: 1.85 +/- 0.15
- Threshold: -100.0 (Passed)
Usage
Load Pyramids.onnx into the Unity ML-Agents environment.
- Downloads last month
- 9
Evaluation results
- mean_reward on ML-Agents-Pyramidsself-reported1.85 +/- 0.15