danieladejumo's picture
Created and train PPO model
802ae06
raw
history blame
172 Bytes
{"mean_reward": -1.880243192511344e-05, "std_reward": 9.931980779962763e-08, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-20T15:26:06.291756"}