ppo-LunarLander-v2 / results.json
hsuyab's picture
first commit for hf rl course unit1
f2aafa3
{"mean_reward": 262.92560840757375, "std_reward": 16.073674224307336, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-16T09:02:51.551849"}