ppo-LunarLander-v2 / results.json
tsfeith's picture
First RL model
7e25e0b verified
{"mean_reward": 256.53489410000003, "std_reward": 20.035126457558704, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-27T14:05:47.726870"}