ppo-LunarLander-v2 / results.json
sohail756's picture
this is the first version of the model and it is as said in the tutorial
dbf3ded verified
raw
history blame
165 Bytes
{"mean_reward": 240.36293809999998, "std_reward": 20.855016555948815, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-01T14:57:53.152677"}