An Overview of Reinforcement Learning Methods for Variable Speed Limit Control

Round 1

Reviewer 1 Report

In this paper a comprehensive review of the reinforcement learning methods is reviewed for a particular application, namely variable speed limit control. The work has covered different aspect of the literature and gives an overview of the research work done in the field using reinforcement learning. Many techniques have been reviewed and critically evaluated. One particular aspect is the use of CNN for VSL control, it is claimed that CNN is 2D technique without the ability to include the special-temporal behaviour of the traffic. However, other deep learning algorithms such as LSTM can accommodate this, which should be included in the review.

The paper is well written and presented, but the use of active voice should be avoided. Please use third person writing style.

The definition of TTT should be in brackets when first mentioned on p7.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

This work presented a review of reinforcement learning methods for control. The paper is written well and organized in good structure. Therefore, I recommend accepting the paper for publication.
The following references which are related to this work could be studied and cited:
# Hsu, R. C., Liu, C. T., & Chan, D. Y. (2011). A reinforcement-learning-based assisted power management with QoR provisioning for human–electric hybrid bicycle. IEEE Transactions on Industrial Electronics, 59(8), 3350-3359.
# Lee, J. S., & Jiang, J. W. (2019). Enhanced fuzzy-logic-based power-assisted control with user-adaptive systems for human-electric bikes. IET Intelligent Transport Systems, 13(10), 1492-1498.
# Han, Z., Zhao, J., Leung, H., Ma, K. F., & Wang, W. (2019). A review of deep learning models for time series prediction. IEEE Sensors Journal.

Author Response

Please see the attachment.

Author Response File: Author Response.docx