ppo-LunarLander-v2 / results.json
jmadeano's picture
[DeepRL] Upload updated PPO trained model for LunarLander-v2
1eacacd
raw
history blame contribute delete
163 Bytes
{"mean_reward": 263.742259302294, "std_reward": 21.464066951542762, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-07T06:36:09.611175"}