PPO-LunarLanderv2 / results.json
jlmarrugom's picture
feat: first PPO LLv2 model
7293198
{"mean_reward": 253.0402729764349, "std_reward": 15.206760117499705, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-25T03:54:29.367255"}