Test1ppo-LunarLander-v2 / results.json
devetle's picture
Upload first PPO LunarLander-v2 trained agent, reward = 171+/-56
db46dbc
raw
history blame contribute delete
No virus
164 Bytes
{"mean_reward": 191.18446577688596, "std_reward": 39.87255501113276, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T08:24:32.745072"}