ppo-LunarLander-v2 / results.json
Zak
PPO LunarLander-v2 from RL course
733a967
raw
history blame
156 Bytes
{"mean_reward": 245.1291392, "std_reward": 9.65515885487694, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-24T08:12:32.360251"}