DeepRL-Class / results.json
Ricardmc99's picture
PPO trained agent on 500,000 timesteps
e8e9073
raw
history blame contribute delete
163 Bytes
{"mean_reward": 59.98451736206143, "std_reward": 64.00513799688656, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-09-06T02:54:05.826844"}