PPO-Galaxian-v5 / results.json
Amankankriya's picture
trained model for ALE/Galaxian-v5 using PPO
54a1f51 verified
raw
history blame
138 Bytes
{"mean_reward": 940.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-21T12:57:31.252524"}