step 8_520_000 . Checkpoint from initial model taken and trained further at a lower learning rate 2nd
4e5ecf3
| {"mean_reward": 317.2, "std_reward": 181.21633480456447, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-22T14:37:29.680369"} |