ppo-LunarLander-v2 / results.json
ag159's picture
First training and evaluation of model
68a7675
raw
history blame contribute delete
156 Bytes
{"mean_reward": 256.7668537, "std_reward": 25.4906971060394, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-23T12:56:35.376599"}