ppo-LunarLander-v2 / results.json
jchristian1's picture
Add trained PPO model for LunarLander-v2 with evaluation metrics and replay video
6d91d92 verified
raw
history blame contribute delete
158 Bytes
{"mean_reward": 277.6296937, "std_reward": 22.152214151442262, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-17T22:52:52.285251"}