| { | |
| "run_id": "SnowballTarget1", | |
| "environment": "SnowballTarget", | |
| "algorithm": "PPO", | |
| "training_steps": 200000, | |
| "mlagents_version": "1.1.0", | |
| "torch_version": "2.2.2+cu121", | |
| "hardware": "Tesla T4", | |
| "metrics_type": "training statistics, not independent evaluation", | |
| "last_reported_training_mean_reward": 25.204545974731445, | |
| "last_reported_step": 200000 | |
| } |