PPO-LL2 / results.json
Cheekydave's picture
PPO model trained on 5m steps
2d40278 verified
raw
history blame contribute delete
158 Bytes
{"mean_reward": 287.2246749, "std_reward": 11.812396363998744, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-23T11:14:57.402104"}