ppo-lunarlander-v2 / results.json

30m training steps with linear learning rate scheduler applied after 15m steps

6881971 over 1 year ago

No virus

165 Bytes

{"mean_reward": 302.96265780000004, "std_reward": 12.170855501809033, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-21T18:20:27.608387"}