ppo_lunar_lander_v2 / results.json
jaymanvirk's picture
272 +/- 11.14, improved PPO LunarLander-v2 trained agent
4870fd1
raw
history blame contribute delete
163 Bytes
{"mean_reward": 261.73759600000005, "std_reward": 18.7168759778072, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-28T20:33:01.827016"}