ppo-Pyramids / evaluation.json
bestdive's picture
Add introductory trained PPO policy and honest evaluation
162021c verified
Raw
History Blame Contribute Delete
3.04 kB
{
"environment": "ML-Agents-Pyramids",
"evaluation_seed": 100002,
"episodes": 112,
"mean_reward": -0.9999999310821295,
"std_reward": 0.0,
"episode_returns": [
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295,
-0.9999999310821295
],
"policy": "deterministic ONNX actions",
"training_seed": 42
}