ppo-LunarLander-v2 / results.json
crossroderick's picture
Tuned PPO agent trained on LunarLander-v2 (1 million timesteps)
257c5fb verified
raw history blame
No virus
158 Bytes
{"mean_reward": 281.9335196, "std_reward": 16.589408548428363, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-26T13:42:59.084369"}