Comparative Analysis of Reinforcement Learning Approaches for Dynamic Pricing of Perishable Goods

Comparative Analysis of Reinforcement Learning Approaches for Dynamic Pricing of Perishable Goods | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Comparative Analysis of Reinforcement Learning Approaches for Dynamic Pricing of Perishable Goods Murali Krishna Panthangi, Vasudevan VN This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6756652/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Dynamic pricing of perishable products is a challenging optimization problem with limited shelf life, random demand, and inventory capacity constraints. Fixed or rule-based price policies fail to change in response to market movements and do not yield maximum revenue. In this research, we consider the use of reinforcement learning (RL) techniques for learning adaptive price policies that maximize profitability and inventory usage. We train and contrast four leading RL methods Deep Q-Networks(DQN), Double DQN(DDQN), Proximal Policy Optimization(PPO) and Quantile Regression DQN(QR-DQN) in a simulated retail setting with price and age sensitivity in demand. We compare the RL agents to fixed-price policies in order to measure revenue, inventory loss, and pricing conduct. Our findings show that PPO attains the maximum revenue with minimal waste, performing better than both baselines and other learning-based methods. Dynamic Pricing Perishable Goods Reinforcement Learning Comparative Study Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6756652","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":472243268,"identity":"23991ec5-546b-4bc9-86a6-4e15ae3338ee","order_by":0,"name":"Murali Krishna Panthangi","email":"data:image/png;base64,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","orcid":"","institution":"Amrita School of Physical Sciences Coimbatore","correspondingAuthor":true,"prefix":"","firstName":"Murali","middleName":"Krishna","lastName":"Panthangi","suffix":""},{"id":472243269,"identity":"5e02f212-2674-494e-81e1-84307771c3fe","order_by":1,"name":"Vasudevan VN","email":"","orcid":"","institution":"Amrita School of Physical Sciences Coimbatore","correspondingAuthor":false,"prefix":"","firstName":"Vasudevan","middleName":"","lastName":"VN","suffix":""}],"badges":[],"createdAt":"2025-05-27 07:38:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6756652/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6756652/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89797607,"identity":"86ef533d-59b0-4437-a4cd-08eed59a0497","added_by":"auto","created_at":"2025-08-25 07:24:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":495868,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6756652/v1_covered_3e08a15c-4657-43be-815b-afcc43dff560.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Comparative Analysis of Reinforcement Learning Approaches for Dynamic Pricing of Perishable Goods","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Dynamic Pricing, Perishable Goods, Reinforcement Learning, Comparative Study","lastPublishedDoi":"10.21203/rs.3.rs-6756652/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6756652/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDynamic pricing of perishable products is a challenging optimization problem with limited shelf life, random demand, and inventory capacity constraints. Fixed or rule-based price policies fail to change in response to market movements and do not yield maximum revenue. In this research, we consider the use of reinforcement learning (RL) techniques for learning adaptive price policies that maximize profitability and inventory usage. We train and contrast four leading RL methods Deep Q-Networks(DQN), Double DQN(DDQN), Proximal Policy Optimization(PPO) and Quantile Regression DQN(QR-DQN) in a simulated retail setting with price and age sensitivity in demand. We compare the RL agents to fixed-price policies in order to measure revenue, inventory loss, and pricing conduct. Our findings show that PPO attains the maximum revenue with minimal waste, performing better than both baselines and other learning-based methods.\u003c/p\u003e","manuscriptTitle":"Comparative Analysis of Reinforcement Learning Approaches for Dynamic Pricing of Perishable Goods","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-18 04:35:26","doi":"10.21203/rs.3.rs-6756652/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a400e45f-2f18-4735-ba0e-8e3ea13fcff1","owner":[],"postedDate":"June 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-25T07:24:30+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-18 04:35:26","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6756652","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6756652","identity":"rs-6756652","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}