ppo-LunarLander-v2 / results.json
Waterboy96's picture
PPO agent, steps = 1024, train = 1e6
6d909b8
raw
history blame contribute delete
165 Bytes
{"mean_reward": 255.27113169813566, "std_reward": 18.035924368625476, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-08T11:13:07.054413"}