{ "mean_reward": 9359.2568359375, "eval_mean_best": 9359.2412109375, "is_deterministic": true, "D": 64, "seed": 7, "algo": "Hybrid-HD-PPO", "env": "InvertedDoublePendulum-v5", "beta_base": 0.7071067690849304, "beta_bands": null, "std_reward": 0.8355045180907786, "ci95_reward": 0.366176, "n_eval_episodes": 20 }