Test2ppo-LunarLander-v2 / results.json
devetle's picture
Upload first PPO LunarLander-v2 trained agent, reward = 260+/-19
21e7473
raw
history blame
165 Bytes
{"mean_reward": 291.62695581952966, "std_reward": 15.402994669000456, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T09:43:42.036621"}