LunarLander-ppo / results.json
lowrollr's picture
PPO default params 2m timesteps 2048 steps
94fba38
raw
history blame contribute delete
164 Bytes
{"mean_reward": 262.24886436474935, "std_reward": 18.90791124521353, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-01T06:46:13.356735"}