ppo-LunarLander-v2 / results.json
dmenini's picture
train: ppo LunarLander-v2 trained agent with long training, higher bs
60965b4
raw
history blame contribute delete
165 Bytes
{"mean_reward": 289.96188468390693, "std_reward": 22.587856484610178, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-03T22:24:35.075922"}