ppo-LunarLander-v2 / results.json
Armageddon
train model more steps
01dce25 verified
raw
history blame contribute delete
165 Bytes
{"mean_reward": 290.01987660000003, "std_reward": 23.350509832517396, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-05T12:22:40.588748"}