ppo_lunar / results.json

lunar lander V0 trained for 500k, n_steps=2048, batch_size=128

0897aec over 2 years ago

163 Bytes

{"mean_reward": 138.45479627160063, "std_reward": 83.1480143465921, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T07:21:18.909136"}