ppo-LunarLander-v2 / results.json
TheBaxes's picture
Add first trained model
aafd038
raw
history blame contribute delete
165 Bytes
{"mean_reward": 255.40817556814008, "std_reward": 21.269076195064468, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-03T00:06:43.006266"}