ppo-LunarLander-v2 / results.json
TeoGal's picture
Trained for 4000000 steps
0db9334 verified
raw
history blame contribute delete
158 Bytes
{"mean_reward": 285.3878727, "std_reward": 18.721335497096682, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-02T18:10:01.513823"}