sb3-ppo-LunarLander-v2 / results.json
joefarrington's picture
Initial commit, using SB3 PPO defaults and trained for 1M timesteps
f57d035
raw
history blame contribute delete
164 Bytes
{"mean_reward": 272.5786489837873, "std_reward": 19.415906403506657, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T21:39:57.380871"}