lunar_lander / results.json
krisia13's picture
Entrenamiento y evaluaci贸n con 500,000 de iteraciones con parametrizaci贸n 3
6cdd42c verified
{"mean_reward": -49.715317899999995, "std_reward": 21.942459786488676, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-06T22:11:58.417434"}