ppo-LunarLander-v2 / results.json
jlse's picture
Trained model with PP0 2048, 0.015 coef
a94ac01 verified
raw
history blame contribute delete
158 Bytes
{"mean_reward": 274.9664157, "std_reward": 17.130410721880885, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-20T15:55:06.177068"}