ppo-LunarLander-v2-6 / results.json
ScrappyCoco666's picture
initial version of PPO LunarLander-v2 trained agent
3d546b1
{"mean_reward": 292.23459945782713, "std_reward": 15.695396003070426, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-11T02:24:23.341533"}