LunarLander-v2-PPO / results.json
745H1N's picture
lunar lander v2 with ppo epochs (10) timestamps (500,000 -> 1000,000)
c743750
{"mean_reward": 271.03430059217396, "std_reward": 12.912696775193375, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-09T10:53:10.731245"}