6c990b7aca7bc7058f5e98ea909e924b-AuthorFeedback.pdf

R2 Why compare to COBYLA instead of BOBYQA?: Thank you for the suggestion! We ran BOBYQA (using nlopt) on robot pushing (mean 9.22) and rover (mean 1.40) and it indeed performs better than COBYLA. Thus, we will replace COBYLA by BOBYQA in all experiments. Note that TuRBO still outperforms both by a large margin. R2 The results of EBO for the robot experiments are quite different from the results on the original paper: The results are consistent and we used the code from the authors.