PCSY-D-25-00011

Reinforcement Learning for Fair and Productive Employment: A Case Study on Wage Theft within the Day-Laborer Community

PLOS Complex Systems

Dear Dr. Kammer-Kerwick,

Thank you for submitting your manuscript to PLOS Complex Systems. After careful consideration, we feel that it has merit but does not fully meet PLOS Complex Systems'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 within 60 days Jul 19 2025 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 complexsystems@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pcsy/ 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 editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. This file does not need to include responses to any formatting updates and technical items listed in the 'Journal Requirements' section below.

* 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, competing interests statement, or data availability statement, please make these updates within the submission form at the time of resubmission. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

We look forward to receiving your revised manuscript.

Kind regards,

Keith Burghardt, Ph.D.

Academic Editor

PLOS Complex Systems

Keith Burghardt

Academic Editor

PLOS Complex Systems

Hocine Cherifi

Editor-in-Chief

PLOS Complex Systems

Journal Requirements:

-->1. Your current Financial Disclosure states, “This research was funded by the National Science Foundation grant “D-ISN: TRACK 1: Collaborative Research: Disrupting Exploitation and Trafficking in Labor Supply Networks: Convergence of Behavioral and Decision Science to Design Interventions” (Award Number 2039983).”. However, your funding information on the submission form indicates that you received funding from “Division of Civil, Mechanical and Manufacturing Innovation”. Please indicate by return email the full and correct funding information for your study and confirm the order in which funding contributions should appear. Please be sure to indicate whether the funders played any role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript.-->--> -->-->2. Please provide a complete Data Availability Statement in the submission form, ensuring you include all necessary access information or a reason for why you are unable to make your data freely accessible. If your research concerns only data provided within your submission, please write "All data are in the manuscript and/or supporting information files" as your Data Availability Statement.-->--> -->-->3. We ask that a manuscript source file is provided at Revision. Please upload your manuscript file as a .doc, .docx, .rtf or .tex.-->--> -->-->4. Please ensure that the Title in your manuscript file and the Title provided in your online submission form are the same.-->--> -->-->5. Your manuscript is missing the following sections: Method. Please ensure these are present, and in the correct order, and that any references to subheadings in your main text are correct. An outline of the required sections can be consulted in our submission guidelines here: -->-->https://journals.plos.org/complexsystems/s/submission-guidelines#loc-parts-of-a-submission-->--> -->-->6. Please upload a copy of Figure 1, 2, 3, 4, 5, 6, 7 which you refer to in your text on page 8, 11, 13, 14, 21, 23, 26. Or, if the figure is no longer to be included as part of the submission please remove all reference to it within the text.-->--> -->-->7. Please provide separate figure files in .tif or .eps format.-->--> -->-->For more information about figure files please see our guidelines: -->-->https://journals.plos.org/complexsystems/s/figures -->-->https://journals.plos.org/complexsystems/s/figures#loc-file-requirements-->--> -->-->8. We have noticed that you have uploaded Supporting Information files, but you have not included a list of legends. Please add a full list of legends for your Supporting Information files after the references list.-->

Additional Editor Comments (if provided):

[Note: HTML markup is below. Please do not edit.]

Reviewers' Comments:

Reviewer's Responses to Questions

-->Comments to the Author

1. Does this manuscript meet PLOS Complex Systems’s publication criteria ? Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe methodologically and ethically rigorous research with conclusions that are appropriately drawn based on the data presented.-->

Reviewer #1: Partly

Reviewer #2: Partly

Reviewer #3: No

**********

-->2. Has the statistical analysis been performed appropriately and rigorously?-->

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: No

**********

-->3. Have the authors made all data underlying the findings in their manuscript fully available (please refer to the Data Availability Statement at the start of the manuscript PDF file)?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception. 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: No

Reviewer #2: Yes

Reviewer #3: Yes

**********

-->4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS Complex Systems 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: Yes

Reviewer #3: Yes

**********

-->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: The manuscript applies reinforcement learning (RL) to address wage theft in day-laborer communities, offering both single- and multi-agent formulations. While the study is innovative and socially relevant, revisions are needed to meet the journal standards. Below are targeted recommendations:

1. Please explicitly articulate the limitations of existing policies/interventions for wage theft and why RL is uniquely suited to address these gaps. Compare with traditional game-theoretic or economic models.

2. Please highlight how the multi-agent RL approach advances beyond prior work (e.g., dynamic adaptation, real-world applicability). Emphasize the novelty of integrating GSMDPs for labor exploitation.

3. Please justify parameter choices (e.g., 30% theft probability, 25% wage loss) with empirical data from prior studies (e.g., [32]) or sensitivity tests.

4. Please clarify how employer/laborer interactions are modeled (e.g., sequential decision-making, reward structures). Include pseudocode or a flowchart differentiating single- vs. multi-agent implementations.

5. Report convergence metrics (e.g., Q-value stability across runs) and validate model outputs against real-world benchmarks (e.g., wage recovery rates).

6. Justify tested success rates (0.1%, 1%, 2%) with policy relevance (e.g., achievable through advocacy). Add effect sizes to quantify policy impact.

7. Use bootstrapping or Bayesian methods for confidence intervals instead of standard deviations. Discuss practical significance of overlapping intervals in Figure 6.

8. Ensure Figures 5–6 clearly distinguish trends (e.g., color-coding for actions) and annotate axes with units. Include a summary table of key findings.

9. Provide a GitHub link or detailed pseudocode in the supplement, highlighting multi-agent logic (e.g., agent_type switching).

Reviewer #2: I was not involved in the original reviews but have access to the author's responses. My position is similar to that of original reviewer 2. While there may have been improvements, there continues to be far too much methodological detail (and repetition) while failing to actually describe the novelty.

1/ There are three aspects for which the method is unclear.

a/ What is the cost to the labourer for reporting? As it stands, the paper simply says that the job ends. If so, there doesn't appear to be any cost - they have still been paid (at the reduced rate) but is there some additional cost such as application fee and/or hassle, or reduced chance of future employment, or that the employer doesn't pay at all instead of paying the reduced amount? These are all very different but this cost is not included in the parameters reported.

b/ Where does the data used to train the LR model come from? The way the paper is written, it suggests that the first 900 or so runs generate data that is used as training data for the analytical runs. But this doesn't really make sense.

c/ You refer to incomplete information in the decision making and that this incompleteness is represented through learning with just state change information. This is somewhat implicit however, it would be good to clarify what is and is not known (which might relate to b).

2/ Original reviewer 2 mentioned the possibility of an analytical solution.

If there is no cost to the labourer for reporting, then they should simply report every time since there is a non-zero probability of a gain. That is, reporting is strictly preferable to not reporting. Regardless, the simplicity of the setup suggests that there is an analytical solution. If X is the expected cost of reporting (and 500 is the value of success) then reporting is strictly preferable to not reporting where 500p > X for p as probability of success. If the LR result is different from this, then that needs to be discussed. However, I suspect that this is related to point 1a, about the unclear consequences of reporting and/or 1c about incomplete information.

3/ If this is a methodological contribution...

The introduction suggests that the contribution is about generalising the methodology. If so, what have you done that could not be done with the existing methodology? What additional knowledge is included and how did this change the outcome?

4/ Overall, further attention is required to focus the paper. It is well written - the words make sense. But it is not actually clear. There are many pages of introduction that provide the background to the stated contributions, but that introduction is far too long and then the paper doesn't really deliver on the contributions in a clear way.

- What are you doing that is new?

- Why is that interesting, what can you solve that you couldn't before and how does that change the answer?

- What does the reader need to know to understand what is new?

Reviewer #3: I identify two main issues with this paper:

The first is the structure of the text. It lacks a clear explanatory introduction setting the context and motivation for this work. The Introduction and the Background sections seem juxtaposed to what used to be the core of the paper (the case study I am guessing). The case study includes in turn some background material (defintions) that logically should appear earlier.

The second and most important issue concerns the validity of the model: the authors take their parameters from a study (ref 32, heavily referenced throughout the paper) that relies on interviews with a small (n<40) non random sample of immigrant workers. Following that, the authors neither perform a formal sensitivity analysis to see how uncertainty about the parameters propagate into their model, nor do they validate the outcomes against real data. The authors should address these issues for the paper to meet publication criteria in my opinion.

**********

-->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.

Do you want your identity to be public for this peer review? If you choose “no”, your identity will remain anonymous but your review may still be made public.

For information about this choice, including consent withdrawal, please see our Privacy Policy .-->

Reviewer #1: No

Reviewer #2: No

Reviewer #3: No

**********

[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.]

Figure resubmission:

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. If there are other versions of figure files still present in your submission file inventory at resubmission, please replace them with the PACE-processed versions.

Reproducibility:

To enhance the reproducibility of your results, we recommend that authors of applicable studies deposit laboratory protocols in protocols.io, where a protocol can be assigned its own identifier (DOI) such that it can be cited independently in the future. Additionally, PLOS ONE offers an option to publish peer-reviewed clinical study protocols. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols

Reinforcement Learning to Develop Policies for Fair and Productive Employment: A Case Study on Wage Theft within the Day-Laborer Community

PCSY-D-25-00011R1

Dear Dr. Kammer-Kerwick,

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 for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at https://www.editorialmanager.com/pcsy/ click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. For questions related to billing, please contact billing support at https://plos.my.site.com/s/.

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 complexsystems@plos.org.

Kind regards,

Keith Burghardt, Ph.D.

Academic Editor

PLOS Complex Systems

Additional Editor Comments (optional):

Congratulations! All suggestions by the reviewers have been addressed. We look forward to seeing your publication on PLOS CS.

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: (No Response)

Reviewer #4: All comments have been addressed

Reviewer #5: All comments have been addressed

Reviewer #6: All comments have been addressed

--------------------

-->2. Does this manuscript meet PLOS Complex Systems's publication criteria ? Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe methodologically and ethically rigorous research with conclusions that are appropriately drawn based on the data presented.-->

Reviewer #1: (No Response)

Reviewer #4: Yes

Reviewer #5: Yes

Reviewer #6: Yes

--------------------

-->3. Has the statistical analysis been performed appropriately and rigorously?-->

Reviewer #1: (No Response)

Reviewer #4: Yes

Reviewer #5: Yes

Reviewer #6: I don't know

--------------------

-->4. Have the authors made all data underlying the findings in their manuscript fully available (please refer to the Data Availability Statement at the start of the manuscript PDF file)?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception. 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: (No Response)

Reviewer #4: Yes

Reviewer #5: Yes

Reviewer #6: No

--------------------

-->5. Is the manuscript presented in an intelligible fashion and written in standard English?<br/><br/>PLOS Complex Systems 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: (No Response)

Reviewer #4: (No Response)

Reviewer #5: Yes

Reviewer #6: Yes

--------------------

-->6. Review Comments to the Author<br/><br/>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: No further comment.

Reviewer #4: the manuscript can be accepted for publication

Reviewer #5: I have studied the manuscript "Reinforcement learning to develop policies for

fair and productive employment: A case study on wage theft within the

day-laborer community" by Kammer-Kerwick and Aldrich, under consideration in

PLOS Complex Systems. I have also carefully considered the three previous

reviewer reports, as well as the authors' detailed response to the reviewers.

This manuscript presents a rigorous and timely contribution that applies

reinforcement learning to develop policies addressing labor exploitation, with

wage theft among day laborers as the motivating case study. The paper is

methodologically sound, presenting both single-agent and multi-agent

reinforcement learning formulations and introducing the use of generalized

semi-Markov processes to better capture the dynamics of sociological systems.

I also believe that the previous revisions have substantially improved the

manuscript by clarifying parameter justifications, adding convergence metrics,

incorporating confidence intervals, and presenting a GitHub repository with

code and documentation.

In summary, I consider this manuscript engaging and well-suited to the scope

of PLOS Complex Systems, as it combines methodological innovation with

real-world relevance, linking complexity-informed modeling to urgent societal

issues in precarious labor and policy design. I have no further comments on

how to improve this work, and therefore, I recommend acceptance in its present

form.

Reviewer #6: The revised version addressed the rprevious comments and recommendations.

--------------------

-->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.

Do you want your identity to be public for this peer review? If you choose “no”, your identity will remain anonymous but your review may still be made public.

For information about this choice, including consent withdrawal, please see our Privacy Policy .-->

Reviewer #1: None

Reviewer #4: No

Reviewer #5: No

Reviewer #6: No

--------------------