ppo-LunarLander-v2 / results.json
AigizK's picture
Parameters: PPO model, batch_size: 32, n_steps: 512, epochs: 10, gamma: 0.999, gae_lambda: 0.95, ent_coef: 0.01, total_timesteps=2000000
7125b9f
raw history blame
No virus
165 Bytes
{"mean_reward": 289.88101479838144, "std_reward": 15.478473777339426, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-14T18:34:32.339531"}