ppo-LunarLander-v2-rerun / results.json
diffrxction's picture
PPO LunarLander-v2 trained agent for deep-rl-course by huggingface
dc57194
{"mean_reward": 219.14086527825893, "std_reward": 100.35172242965172, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-08T18:57:38.776665"}