ppo-LunarLander-v2 / results.json
rynsy's picture
Longer training, tweaked parameters
53fd7c9
{"mean_reward": 279.6507906382062, "std_reward": 12.06202438478162, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T15:30:52.747930"}