ppo-LunarLander-v2 / results.json
crossroderick's picture
Tuned PPO agent trained on LunarLander-v2 (1 million timesteps)
958737f verified
raw
history blame
158 Bytes
{"mean_reward": 282.3083673, "std_reward": 20.045812325246818, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-26T13:40:40.058680"}