rl-ppo-LunareLander-v2-1 / results.json
flaging's picture
first version of ppo model
b71b427 verified
{"mean_reward": 257.5483635, "std_reward": 20.946424136688936, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-20T00:46:16.571772"}