A Sequence-Based Hyper-Heuristic for Traveling Thieves

Round 1

Reviewer 1 Report

At present, there is little research on solving "Traveling Thief Problem (TTP)" problems by using a Hyper-heuristic algorithm. This paper proposes a sequence based selection Hyper-heuristic algorithm, which verifies the proposed method by generating several groups of TTP instances with different parameters and analyzes the performance of the model. The experimental results show that the proposed method is superior to the random generated sequence and the general sequence is superior to the special sequence of each instance. Some suggestions are given as follows.

1.      There are some expression errors such as page 4, Y ∈ ZT2, the eleven rows of 2.1.3.Please check this paper and correct them.

2.      In real life, item prices may be calculated by weight rather than by number such as rice, can your algorithm solve this problem?

3.      The experimental results show that the proposed algorithm is better than the random selection scheme, but can you compare the gap between maximum profits in some problems the best solution can be got? Or can you compare the result with some easier algorithm?(such as choose the route only by TSP and choose items only by maximum profit ratio in the last few cities )  

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

This paper proposes a sequence-based selection hyper-heuristic and assesses its feasibility when solving the  Traveling Thief Problem.

 

The authors may need to take into consideration the following issues:

 

1. The aconclusion section is a little bit long. I suggest authors can add reduce some paragraphs of this section.

 

2. References only have 12 references have 3-years (since 2020) publications. Thus, I suggest the author may add more description about the state-of-the-art techniques and to cite some top journals of the article. 

 

3. I suggest the simulation results can be listed as in Tables (such as cpu computation time, performance,...etc)

 

4. I would like to see if the SOTA algorithms can be used to compare the performance of the proposed model in this article. In addition, the Wilcoxon rank sum test to verify proposed method is needed. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

All issues have been addressed