ppo-LunarLander-v2 / results.json
oliar's picture
Tried running the lunar lander PPO with 10mil timestamps; limited success.
9099526
raw
history blame
165 Bytes
{"mean_reward": 302.84871481441974, "std_reward": 14.520752642652598, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-28T16:59:05.465546"}