LunarLander-v2-PPO / results.json

Improve PPO trained agent to 276.44 +/- 21.651967758051594

eac14dc about 2 years ago

164 Bytes

{"mean_reward": 255.12738523909792, "std_reward": 64.65579970572723, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-12T03:35:36.942244"}