ppo_lunar_lander_1m / results.json
fgmckee's picture
Upload PPO LunarLander-v2 trained agent. 1m timesteps default hyperparameters
ed38df9
{"mean_reward": 264.6234400626884, "std_reward": 15.43961815289653, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T12:51:42.827317"}