PPO-LunarLander-v2 / results.json
Anren's picture
Update: Trained on 1M steps
dabfff6 verified
raw
history blame contribute delete
165 Bytes
{"mean_reward": 250.52042139999998, "std_reward": 17.605433130562638, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-23T16:41:40.893772"}