ppo-LunarLander-v2 / results.json
MarcusAGray's picture
Trained for 5 million timesteps
5a3d038
{"mean_reward": 281.8720128712791, "std_reward": 14.727765106575543, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T13:41:27.247978"}