ppo-LunarLander-v2 / results.json
sigalaz's picture
First PPO model
cba1184
{"mean_reward": 237.1476707205166, "std_reward": 93.3205473746058, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-15T16:55:58.705918"}