ppo-LunarLander-v2-first / results.json
BrBlitz's picture
First try with some changes to default
fd11e0c
{"mean_reward": 256.32537909999996, "std_reward": 19.96754014695984, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-05T22:41:49.869175"}