LazyAct: Lazy actor with dynamic state skip based on constrained MDP

Hongjie Zhang; Zhenyu Chen; Hourui Deng; Chaosheng Feng

doi:10.1371/journal.pone.0318778

Peer Review History

Original SubmissionJune 28, 2024
25 Sep 2024 Decision Letter - Manoharan Premkumar, Editor PONE-D-24-26037LazyAct: Lazy Actor with Dynamic State Skip based on Constrained MDPPLOS ONE Dear Dr. Zhang, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. Please submit your revised manuscript by Nov 09 2024 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript: A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Manoharan Premkumar Academic Editor PLOS ONE Journal requirements: When submitting your revision, we need you to address these additional requirements. 1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf 2. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, all author-generated code must be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse. 3. Thank you for stating the following financial disclosure: “This work was supported by the Sichuan Science and Technology Program (No. 2022NSFSC0552).” Please state what role the funders took in the study. If the funders had no role, please state: "The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript." If this statement is not correct you must amend it as needed. Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf. 4. Thank you for stating the following in the Acknowledgments Section of your manuscript: “This work was supported by the Sichuan Science and Technology Program (No. 2022NSFSC0552).” We note that you have provided funding information that is currently declared in your Funding Statement. However, funding information should not appear in the Acknowledgments section or other areas of your manuscript. We will only publish funding information present in the Funding Statement section of the online submission form. Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Currently, your Funding Statement reads as follows: “This work was supported by the Sichuan Science and Technology Program (No. 2022NSFSC0552).” Please include your amended statements within your cover letter; we will change the online submission form on your behalf. 5. We note that Figures 1 and 9 in your submission contain copyrighted images. All PLOS content is published under the Creative Commons Attribution License (CC BY 4.0), which means that the manuscript, images, and Supporting Information files will be freely available online, and any third party is permitted to access, download, copy, distribute, and use these materials in any way, even commercially, with proper attribution. For more information, see our copyright guidelines: http://journals.plos.org/plosone/s/licenses-and-copyright. We require you to either (1) present written permission from the copyright holder to publish these figures specifically under the CC BY 4.0 license, or (2) remove the figures from your submission: 1. You may seek permission from the original copyright holder of Figures 1 and 9 to publish the content specifically under the CC BY 4.0 license. We recommend that you contact the original copyright holder with the Content Permission Form (http://journals.plos.org/plosone/s/file?id=7c09/content-permission-form.pdf) and the following text: “I request permission for the open-access journal PLOS ONE to publish XXX under the Creative Commons Attribution License (CCAL) CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). Please be aware that this license allows unrestricted use and distribution, even commercially, by third parties. Please reply and provide explicit written permission to publish XXX under a CC BY license and complete the attached form.” Please upload the completed Content Permission Form or other proof of granted permissions as an "Other" file with your submission. In the figure caption of the copyrighted figure, please include the following text: “Reprinted from [ref] under a CC BY license, with permission from [name of publisher], original copyright [original copyright year].” 2. If you are unable to obtain permission from the original copyright holder to publish these figures under the CC BY 4.0 license or if the copyright holder’s requirements are incompatible with the CC BY 4.0 license, please either i) remove the figure or ii) supply a replacement figure that complies with the CC BY 4.0 license. Please check copyright information on all replacement figures and update the figure caption with source information. If applicable, please specify in the figure caption text when a figure is similar but not identical to the original image and is therefore for illustrative purposes only. 6. Please include captions for your Supporting Information files at the end of your manuscript, and update any in-text citations to match accordingly. Please see our Supporting Information guidelines for more information: http://journals.plos.org/plosone/s/supporting-information. Additional Editor Comments: Address the points raised by the reviewers. Give proper response and action. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes Reviewer #2: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes ****** 3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes Reviewer #2: Yes ****** 4. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes Reviewer #2: No ****** 5. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: General comments - The manuscript introduced an novel algorithm namely LazyAct, which claimed to significantly reduce the number of inferences while preserving the quality of policy. Theoretically the method proposed in the manuscript demonstrated feasibility of inference reducing, however, there are still a few things need to improve before the manuscript being accepted. In detail comments - Normally, a multi-agent system to deal with a complex task chain such as game playing, will include a consideration process such as planning, consideration, executing etc. These seems not been mentioned in the manuscript. - Regarding to Eq (4), not sure why you provide argmin prior to max, since it seems a backward computation. - With MAPPO scheme included, authors’ written down “employs a framework of centralized learning with decentrallized execution ”, it seem like another “pull-push” process, cannot understand why you do this repeat and reverse though, please make additional discussion about neccessity. - Similar as prior question, once using MAPPO framework for executing-reflexion, the purpose to feedback providing referring to partial observation need to discuss, particularly outperforming among other methods. For now, I could not imagine other outperform arpart from computing deduction. - With concluding remarks in abstract, “Lazyact reduces the number of inferences by approximately 80% and 40%” , however results does not seems to match the justification, as I have not yet seen any discussion regarding to time efficiency or computational infrastructure saving etc. Reviewer #2: Dear Authors I would like to congratulate you on a very good approach. From my view, it is a valuable addition to the literature. The only minor revision required is to improve the English language of the manuscript. ****** 6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: No Reviewer #2: Yes: Ghassan Abdul-Majeed ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0318778.r001
Revision 1
1 Nov 2024 Author Response Dear academic editor and reviewers, Thank you for providing the opportunity to revise our manuscript titled "LazyAct: Lazy Actor with Dynamic State Skip based on Constrained MDP" (Manuscript ID: PONE-D-24-26037). We appreciate the valuable feedback from the academic editor and reviewers, which has helped us improve the quality of our work. Below, we address each point raised and provide a detailed rebuttal or explanation for the changes made. Addressing the Comments of the Academic Editor: 1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. Response: We acknowledge the importance of adhering to the journal’s style requirements and file naming conventions. We have reviewed the PLOS ONE author guidelines and have made the necessary adjustments to ensure our manuscript complies with the specified standards. 2. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. Response: We are confident that these actions fully comply with PLOS ONE’s guidelines on code sharing. We are committed to open science practices and believe that sharing our code will contribute to the advancement of the field. 3. Please include this amended Role of Funder statement in your cover letter. Response: We have included the amended Role of Funder statement in our cover letter as requested. 4. Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Response: We have removed all funding-related text from the manuscript. 5. We note that Figures 1 and 9 in your submission contain copyrighted images. Response: We have removed the Figure 1 and revised Figure 9, deleting the copyrighted images. 6. Please include captions for your Supporting Information files at the end of your manuscript. Response: Captions for the Supporting Information files have been added to the 'Supporting information' of the manuscript. Addressing the Comments of Reviewer 1: 1. Normally, a multi-agent system to deal with a complex task chain such as game playing, will include a consideration process such as planning, consideration, executing etc. These seems not been mentioned in the manuscript. Response: Thank you for the suggestion. You pointed out that our paper did not address the consideration process of multi-agent systems when facing complex task chains, such as planning, thinking, and executing. We have supplemented this content in our paper "LazyAct for Multi-agents based on MAPPO" and explained how LazyAct integrates with multi-agent systems. In multi-agent systems, planning, consideration and execution are key steps that constitute the process of decision-making. Our paper focuses on model-free reinforcement learning, while model-based algorithms will be further studied in future work. In the model-free methods, agents have no knowledge of the environment, including rules and rewards. Agents learn policy through trial and error. Planning involves determining how to achieve goals or complete tasks. Planning can be centralized or decentralized. In centralized planning, there is a central decision-maker for all agents. In decentralized planning, each agent independently makes its own action plan. The MAPPO is a form of decentralized planning. Each agent outputs actions based on its observations and receives environmental rewards, adjusting actions to maximize cumulative rewards. Processes like planning are implicitly included in the policy π, as π has already learned the long-term planning for task completion through numerous interactions. LazyAct evaluates the importance of states and determines the skip length. LazyAct uses a neural network to evaluate the importance of states and decides whether to skip them based on this importance. If a state is skipped, LazyAct generates a series of repeated actions based on the current state and the skip length. LazyAct can be combined with other consideration processes, such as planning and thinking. For example, LazyAct can be used in the planning phase to reduce the number of states that need consideration, thus improving planning efficiency. 2. Regarding to Eq (4), not sure why you provide argmin prior to max, since it seems a backward computation. Response: Thank you for the suggestion. We employ the Primal Dual Optimization (PDO) method in constrained reinforcement learning. By using Lagrange multipliers, we transform the constrained problem into an unconstrained min-max optimization problem, where 'α' is the Lagrange multiplier. Intuitively, 'α' balances the cumulative reward gained by the agent and the cumulative computational cost. When 'α' is 0, it means the computational cost is not considered. As 'α' increases, the learned policy tends to reduce the computational cost. In Equation 4, the inner max operation represents maximizing cumulative reward given 'α', which considers the computational cost. The outer argmin operation checks if the current policy meets the constraints. If the constraints are met, 'α' is set to 0, prompting the inner layer to maximize cumulative reward. If the constraints are violated, 'α' increases, steering the inner policy towards reducing computational cost to ensure the policy meets the constraints. Through alternating training of the inner and outer layers, It converges to the optimal 'α' that satisfies the constraints, along with the corresponding policy π. 3. With MAPPO scheme included, authors’ written down “employs a framework of centralized learning with decentrallized execution ”, it seem like another “pull-push” process, cannot understand why you do this repeat and reverse though, please make additional discussion about neccessity. Response: Thank you for the suggestion. You pointed out the "centralized learning, decentralized execution" framework of the MAPPO algorithm and the role of LazyAct within this framework. Our explanation of the MAPPO framework in the paper was not clear enough, and there may have been misunderstandings about the role of LazyAct. We provide additional clarification here: The MAPPO algorithm uses the "centralized learning, decentralized execution" framework, as shown in Figure 3 of the paper "LazyAct for Multi-agents based on MAPPO." Multiple agents interact independently with the environment and send experience data to a central learner. The central learner updates the Actor and Critic networks with this data and sends the updated Actor network back to each agent. After training, the Critic network is no longer used, and only the Actor network interacts with the environment. Our 'skip' is a branch inserted into the Actor network, used to evaluate whether subsequent states can adopt repeated actions, thus saving computation for the agents. The 'skip' actions are integrated with the original actions during training, guided by the Critic network. Regarding the "repeat and reverse" process you mentioned, we understand your confusion. In fact, LazyAct does not use a "repeat and reverse" process. The core mechanism of LazyAct is to let each agent in MAPPO reduce the computational cost of policy evaluation by dynamically skipping unimportant states. This mechanism is compatible with the MAPPO framework and can help enhance its performance. We have revised the paper "LazyAct for Multi-agents based on MAPPO" according to your comments and provided a more detailed explanation of the MAPPO framework and the role of LazyAct. We believe that LazyAct can be effectively integrated into the MAPPO framework and help improve the efficiency of multi-agent systems. 4. Similar as prior question, once using MAPPO framework for executing-reflexion, the purpose to feedback providing referring to partial observation need to discuss, particularly outperforming among other methods. For now, I could not imagine other outperform arpart from computing deduction. Response: Thank you for the suggestion. As described in Figure 3 of "LazyAct for Multi-agents based on MAPPO," the MAPPO process is a decentralized execution model. Each agent can only observe its local observations o, without access to the global state s or communication with other agents. Therefore, agents make decisions based on partially observable states. Unlike a centralized execution model, the action space in MAPPO does not increase with the number of agents. Moreover, the multi-agent system can decompose the complex joint action space into several smaller subspaces. This allows each agent to focus on and execute only a part of the actions, simplifying the decision-making process. Regarding the 'skip', compared to TempoRL, LazyAct can better control the proportion of skips to meet constraints, such as requiring only a certain percentage of agents to make decisions in each state. We have presented experimental results of LazyAct in partially observable environments in the paper, such as win rates and skip proportions in SMAC tasks. The results show that LazyAct can significantly reduce computational costs without sacrificing policy quality and meet specific constraint. 5. With concluding remarks in abstract, “Lazyact reduces the number of inferences by approximately 80% and 40%” , however results does not seems to match the justification, as I have not yet seen any discussion regarding to time efficiency or computational infrastructure saving etc. Response: Thank you for the suggestion. You correctly pointed out that the paper did not fully discuss the time and computational savings of LazyAct, which is significant. There was indeed a shortfall in the paper. To better illustrate the advantages of LazyAct, we have supplemented the experimental section with results on time and computational savings (FLOPs). The results show that LazyAct significantly reduces the number of inferences while maintaining policy performance, and substantially saves time and FLOPs. The revised version of the paper includes a detailed explanation in the "Time and FLOPs Saving" section. We have revised the abstract and discussion sections based on the additional experimental results to more accurately reflect the benefits of LazyAct. We believe that the time and computational savings offered by LazyAct increase its practical value in real-world applications. Addressing the Comments of Reviewer 2: 1. I would like to congratulate you on a very good approach. From my view, it is a valuable addition to the literature. The only minor revision required is to improve the English language of the manuscript. Thank you for the feedback. We will address the minor revision by improving the English language throughout the manuscript. We will have the manuscript professionally edited to ensure clarity and grammatical accuracy. We highlight changes in ‘Revised Manuscript with Track Changes’ made to the original version. The following lists the main revisions made to the paper: 1) In abstraction: However, the high computational cost of policies based on deep neural networks restricts their practical application. 2) Line 5: and large language models [3, 4], etc. 3) Line 22: Dynamic neural networks can accelerate speed 4) Line 39: a duration is considered as a high-level action 5) Line 48: to derive the optimization objective 6) Line 50-52: In the context of multi-agents systems, we constrain the number of decisions in each state. And we maximize the cumulative reward of the task. In particular, 7) Line 58-59: It is designed to maximize cumulative rewards while enabling it to skip states that are unimportant. 8) Line 81: cluster centers, remarkably reducing the storage 9) Line 102: learning algorithms to lock into important recognition 10) Line 110: Brainstorm fills the gap and through its proposed dynamic optimization 11) Line 126: between computational efficiency, accuracy and robustness, 12) Line 151: The above mentioned action repeat method mainly focuses on single agent 13) Line 163: This sequence of actions is then sent to the 14) Line 173: LazyAct for Single-agent based on IMPALA 15) Line 175: IMPALA stands for a distributed 16) Line 178: The Learner updates the policy network parameters 17) Line 182: Formal Problem Definition 18) Line 218: Drawing from the definition provided 19) Line 228: LazyAct for Multi-agents based on MAPPO 20) Line 288: agent’s observation o 21) Line 294: Unconstrained Pre-training and Constrained Fine-tuning 22) Line 306: is set too large 23) Line 316: Training Setups 24) Line 339: It provides an evaluation of the skip based on the state and action. 25) Line 368: applicable to multi-agents tasks In conclusion, we have carefully addressed all the comments and suggestions provided by the academic editor and reviewers. We believe that the revised manuscript is now significantly improved and better aligned with the journal's standards. We hope that the manuscript is now suitable for publication. Thank you again for your valuable feedback and the opportunity to revise our work. Sincerely, Hongjie Zhang College of Computer Science, Sichuan Normal University, Chengdu, China zhanghongjie@sicnu.edu.cn Attachments Attachment Submitted filename: Response to Reviewers.docx https://doi.org/10.1371/journal.pone.0318778.r002
22 Jan 2025 Decision Letter - Manoharan Premkumar, Editor LazyAct: Lazy Actor with Dynamic State Skip based on Constrained MDP PONE-D-24-26037R1 Dear Dr. Zhang, We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements. Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication. An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, please contact our Author Billing department directly at authorbilling@plos.org. If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. Kind regards, Manoharan Premkumar Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation. Reviewer #1: All comments have been addressed ******** 2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes ****** 5. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes ****** 6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: General comments The manuscript could be accepted since all my recommendations been addressed. In detail comments - Normally, a multi-agent system to deal with a complex task chain such as game playing, will include a consideration process such as planning, consideration, executing etc. These seems not been mentioned in the manuscript. [√] - Regarding to Eq (4), not sure why you provide argmin prior to max, since it seems a backward computation. 【√】 - With MAPPO scheme included, authors’ written down “employs a framework of centralized learning with decentrallized execution ”, it seem like another “pull-push” process, cannot understand why you do this repeat and reverse though, please make additional discussion about neccessity.【√】 - Similar as prior question, once using MAPPO framework for executing-reflexion, the purpose to feedback providing referring to partial observation need to discuss, particularly outperforming among other methods. For now, I could not imagine other outperform arpart from computing deduction. 【√】 - With concluding remarks in abstract, “Lazyact reduces the number of inferences by approximately 80% and 40%” , however results does not seems to match the justification, as I have not yet seen any discussion regarding to time efficiency or computational infrastructure saving etc. 【√】 ****** 7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: No ******** https://doi.org/10.1371/journal.pone.0318778.r003
Formally Accepted
28 Jan 2025 Acceptance Letter - Manoharan Premkumar, Editor PONE-D-24-26037R1 PLOS ONE Dear Dr. Zhang, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset If revisions are needed, the production department will contact you directly to resolve them. If no revisions are needed, you will receive an email when the publication date has been set. At this time, we do not offer pre-publication proofs to authors during production of the accepted work. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few weeks to review your paper and let you know the next and final steps. Lastly, if your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. If we can help with anything else, please email us at customercare@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Manoharan Premkumar Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0318778.r004

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .