lunar_lander / results.json
krisia13's picture
Entrenamiento y evaluaci贸n con 1,000,000 de iteraciones
dce6ac5 verified
{"mean_reward": 224.7323077, "std_reward": 74.24538545595506, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-17T17:27:16.524484"}