ppo2-LunarLander-v2 / results.json
CAVJ's picture
Este es mi primer entrenamiento del algoritmo PPO LunarLander-v2
a54ad17 verified
{"mean_reward": 264.4338118204288, "std_reward": 21.85613587716865, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-20T21:44:57.588679"}