ppo-LunarLander-v2 / results.json
livac's picture
initial version of PPO for LunarLander-v2
d5179c1
{"mean_reward": 275.4941696193308, "std_reward": 18.888339879484985, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T11:08:47.154132"}