SeanShih
/

REINFORCE-PixelCopter

Reinforcement Learning

Pixelcopter-PLE-v0

reinforce

custom-implementation

deep-rl-class

Eval Results (legacy)

Model card Files Files and versions

xet

Community

REINFORCE-PixelCopter / results.json

SeanShih

Upload folder using huggingface_hub

c6b1667 verified 5 days ago

Raw History Blame Contribute Delete

204 Bytes

{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 6.5, "std_reward": 5.987486951969082, "certification_score": 0.5125130480309181, "n_evaluation_episodes": 10, "eval_datetime": "2026-10-27T23:44:01.504195"}