| { | |
| "mean_reward": -84.5999984741211, | |
| "eval_mean_best": -97.3499984741211, | |
| "is_deterministic": true, | |
| "D": 16, | |
| "seed": 123, | |
| "algo": "HD-PPO", | |
| "env": "Acrobot-v1", | |
| "beta_base": 1.0, | |
| "beta_bands": null, | |
| "std_reward": 11.408510089284642, | |
| "ci95_reward": 5.0, | |
| "n_eval_episodes": 20 | |
| } | |