ppo-LunarLander-v2 / results.json
LookParOf's picture
Model trained on 1.000.500 steps
7c30dc1
{"mean_reward": 259.6508567671663, "std_reward": 16.92485781638569, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-23T16:20:03.044890"}