ppo-LunarLander-v2 / results.json
vind's picture
Upload trained PPO model
6c882aa
{"mean_reward": 271.06430574199885, "std_reward": 20.009913557032963, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-10T08:35:43.199397"}