results_D512_teacher.json

{
  "mean_reward": 2338.0703125,
  "eval_mean_best": 2338.070556640625,
  "is_deterministic": true,
  "D": 512,
  "seed": 7,
  "algo": "Hybrid-HD-PPO",
  "env": "InvertedDoublePendulum-v5",
  "beta_base": 0.7071067690849304,
  "beta_bands": null
}