PPO-LL2 / results.json
AliSouliman's picture
agent trained for 10**6 steps
5eea040 verified
raw
history blame contribute delete
165 Bytes
{"mean_reward": 231.84997390000004, "std_reward": 22.449043550545873, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-18T11:37:06.468578"}