ppo-LunarLander-v2 / results.json
jules654's picture
Lunar lander PPO agent 1M steps, default config
5026f6a
{"mean_reward": 244.97843858782375, "std_reward": 17.95829918801396, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-09T07:14:59.071080"}