lander-go-fast / results.json
jgerbscheid's picture
basic PPO model trained on local pc for 4M timesteps
f39177b
raw
history blame
164 Bytes
{"mean_reward": 292.8105637090458, "std_reward": 15.853610343190041, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T19:42:41.188987"}