ppo-LunarLander-v2 / results.json
agustinl's picture
Improved PPO-model for LunarLander-v2 using hyperparameter tuning
9ab81b2
{"mean_reward": 272.9347489, "std_reward": 12.239855668048078, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-19T01:52:22.980927"}