evaluation.json

{
  "environment": "SnowballTarget",
  "episodes": 20,
  "mean_reward": 24.75,
  "std_reward": 2.384848003542364,
  "episode_rewards": [
    17.0,
    26.0,
    22.0,
    26.0,
    23.0,
    26.0,
    27.0,
    23.0,
    25.0,
    27.0,
    26.0,
    25.0,
    26.0,
    24.0,
    22.0,
    28.0,
    25.0,
    26.0,
    25.0,
    26.0
  ],
  "model_file": "/content/course-models/ppo-SnowballTarget/SnowballTarget.onnx",
  "seed": 12345,
  "deterministic": true
}