ppo-LunarLander-v2 / results.json
muks's picture
Upload PPO LunarLander-v2 agent trained for 500000 timesteps
41de170
{"mean_reward": 121.86650565896196, "std_reward": 96.83782917731901, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T11:20:46.071480"}