An Intelligent Access Channel Algorithm Based on Distributed Double Q Learning
Round 1
Reviewer 1 Report
1. what do authors mean by each node users two Q-learning in abstract?
2. Since the article address external malicious jamming, more explanation on that should be provided in the introduction before actually elaborating the related literature on it.
3. Readability is low. Some sentences are poorly written. Example "
a. Each user distributed computing and distributed execution, and hardware performance requirements are not high, good scalability, strong processing power.
b." Sentence on line 38-39 on page 1 can be rewritten.
c. Line 57-58 on page 2 can we rewritten.
4. What is signal malicious jamming? How does it effect the users? How is it simulated in the paper?
5. Why base station can only successfully receive users in user set ( Sn')?
6. Anti-jamming algorithm is proposed to address equation 1. However, equation 1 is not clearly explained nor the rationale behind it.
7. What is reason behind selection of 3 jamming channels out of 5? How would any other selection change the results?
Author Response
Please see the attachment
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The article from a methodological point of view meets the expectations of a scientific article. The authors establish clear categories of analysis and comprehensively explain the procedure used machine learning models. The methodology is also very clear and well worked out from a practical point of view.
Minors
Lines 85-90 are for the contribution of this paper.
I had a little bit of uncertainties as follows:
Most use double deep Q-learning more than double Q-learning. In other words, machine learning and deep learning are used together. I wonder what made you use only “double Q-learning. Moreover, the distributed deep Q-learning is already used in various application fields (Referencs [1] and [2]), and such a software framework is proposed, providing an opportunity to be reusable. I'm curious about what made you didn't use the framework that was already developed.
References:
[1] Kevin Chavez, Hao Yi Ong, and Augustus Hong, “Distributed Deep Q-Learning”.
[2] Van-Hai Bui, Akhtar Hussain, and Hak-Man Kim, IEEE TRANSACTIONS ON SMART GRID, VOL. 11, NO. 1, JANUARY 2020, “Double Deep Q-Learning-Based Distributed Operation of Battery Energy Storage System Considering Uncertainties”.
Author Response
Please see the attachment
Author Response File: 
Author Response.docx
