ppo-LunarLander-v2 / results.json
ZivK's picture
Inital trained ppo model of LunarLander-v2
3966343
{"mean_reward": 262.1690474, "std_reward": 17.213018608404187, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-11T19:30:49.522919"}