ppo-Walker2d-v4 / results.json
Amankankriya's picture
trained model for Walker2d-v4 using PPO
cb2fe51 verified
{"mean_reward": 4275.635702377558, "std_reward": 20.725993879217853, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-24T11:52:34.211153"}