ppo-LunarLander-v2-1E6 / results.json
hdeavila's picture
Mi primer agente entrenado de luna lander con PPO LunarLander-v2 trained agent 1E6 iter
852750c verified
{"mean_reward": 248.5527334, "std_reward": 18.430452812031074, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-14T03:34:33.923978"}