ppo-LunarLander-v2 / results.json
PlankyxD's picture
LunarLander solution using stable baselines' Proximal Policy Optimization
3907932
raw
history blame contribute delete
165 Bytes
{"mean_reward": 242.57235780000002, "std_reward": 47.653545296474604, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-24T12:00:54.815537"}