ppo-LunarLander-v2 / results.json
KnoY's picture
上传 PPO 训练的 LunarLander-v2 智能体
cbe19db verified
{"mean_reward": 253.12674879999994, "std_reward": 21.978115264691212, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-21T12:38:32.065592"}