ppo_lunar_lander-v2 / results.json
bobobert4's picture
1M learn steps, learning_rate 5e-5, n_steps 800, ent_coef 5e-2
162146e
raw
history blame
164 Bytes
{"mean_reward": 201.53706459999998, "std_reward": 84.42538189280488, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-04T01:56:14.054035"}