ppo-LunarLander-v2 / results.json
SwePalm's picture
more training
caebd8d
raw
history blame contribute delete
164 Bytes
{"mean_reward": 284.4650316767707, "std_reward": 14.714864951130355, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-10T22:04:57.194038"}