TEST2ppo-LunarLander-v2 / results.json
hvorost's picture
Upload PPO LunarLander-v2 trained agent total timespels = 7kk
aa165b6
raw
history blame contribute delete
165 Bytes
{"mean_reward": 120.52832924454128, "std_reward": 100.06334943293541, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-22T12:14:37.346211"}