ppo-LunarLander-v2 / results.json
alicjak's picture
PPO model trained for LunarLander-v2 environment
7b86ada
raw
history blame contribute delete
165 Bytes
{"mean_reward": 241.75876252435177, "std_reward": 13.597307053018138, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T14:15:59.509514"}