Reinforcement Learning for Real-World Non-Stationary Systems: An Observation-Aware Survey

Reinforcement Learning for Real-World Non-Stationary Systems: An Observation-Aware Survey | 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 Systematic Review Reinforcement Learning for Real-World Non-Stationary Systems: An Observation-Aware Survey Yugam Padha This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8701502/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 Reinforcement learning (RL) has achieved notable success in simulated environments and controlled benchmarks, yet its deployment in real-world, safety-critical systems remains limited. Practical settings such as robotics, healthcare, and industrial control are characterized by partial and noisy observability, costly information acquisition, limited and imbalanced data, and non-stationary dynamics, all of which violate standard assumptions underlying classical RL formulations. A growing body of work has shown that these challenges are tightly coupled: limitations in observation fundamentally shape learning efficiency, robustness, and safety. This article presents a survey and synthesis of recent reinforcement learning literature through the lens of observation-aware decision making. Rather than proposing new algorithms, we organize existing model-free, model-based, and offline RL methods according to how they control information acquisition, represent uncertainty, and adapt under distribution shift. We review theoretical and empirical results on partial observability, data imbalance, safety constraints, and non-stationarity, highlighting common structural assumptions and failure modes across approaches. By unifying these themes, the survey clarifies how observation design influences policy learning, evaluation, and deployment reliability. We conclude by identifying open methodological challenges and directions for future research in reinforcement learning for real-world, non-stationary environments. Reinforcement learning Partial observability Non-stationary environments Safety and robustness Model-based reinforcement learning 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-8701502","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Systematic Review","associatedPublications":[],"authors":[{"id":580925532,"identity":"e17a1cf7-46a9-42e2-b831-4d976ec50f0a","order_by":0,"name":"Yugam Padha","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIiWNgGAWjYBADxg0MzAeAtIQMKVrYEkBaeEjRwmMAYhDWYnAj/eKnmzvsZLezn/n86kaNBQ8D++GjG/BrySmWzj2TbLyzJ3ebdc4xoMN40tJuENCSIJ3bxpy44UDuNuMcNqAWCR4zQlqSf+e21SduOP/mmXHOP6K0pB8D2nI4ccONHObHuW1EaJE884bNOvfMceMNN56ZMef2SfCwEfIL3/H0x7dzd1TLbjif/Phzzrc6OX72w8fwalE4AIwOxgYwm00CTOJTDgLyDewPYFqYPxBSPQpGwSgYBSMTAACcmFFaAdBVswAAAABJRU5ErkJggg==","orcid":"","institution":"University of Jammu","correspondingAuthor":true,"prefix":"","firstName":"Yugam","middleName":"","lastName":"Padha","suffix":""}],"badges":[],"createdAt":"2026-01-26 14:53:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8701502/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8701502/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104317628,"identity":"94d6548d-41b2-4365-a376-aa5171ece1fe","added_by":"auto","created_at":"2026-03-10 12:28:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":858064,"visible":true,"origin":"","legend":"","description":"","filename":"rlreviewpaperrev1JAIR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8701502/v1_covered_df345246-321a-48ca-8436-a9c5899b9277.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Reinforcement Learning for Real-World Non-Stationary Systems: An Observation-Aware Survey","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Reinforcement learning, Partial observability, Non-stationary environments, Safety and robustness, Model-based reinforcement learning","lastPublishedDoi":"10.21203/rs.3.rs-8701502/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8701502/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eReinforcement learning (RL) has achieved notable success in simulated environments and controlled benchmarks, yet its deployment in real-world, safety-critical systems remains limited. Practical settings such as robotics, healthcare, and industrial control are characterized by partial and noisy observability, costly information acquisition, limited and imbalanced data, and non-stationary dynamics, all of which violate standard assumptions underlying classical RL formulations. A growing body of work has shown that these challenges are tightly coupled: limitations in observation fundamentally shape learning efficiency, robustness, and safety. This article presents a survey and synthesis of recent reinforcement learning literature through the lens of observation-aware decision making. Rather than proposing new algorithms, we organize existing model-free, model-based, and offline RL methods according to how they control information acquisition, represent uncertainty, and adapt under distribution shift. We review theoretical and empirical results on partial observability, data imbalance, safety constraints, and non-stationarity, highlighting common structural assumptions and failure modes across approaches. By unifying these themes, the survey clarifies how observation design influences policy learning, evaluation, and deployment reliability. We conclude by identifying open methodological challenges and directions for future research in reinforcement learning for real-world, non-stationary environments.\u003c/p\u003e","manuscriptTitle":"Reinforcement Learning for Real-World Non-Stationary Systems: An Observation-Aware Survey","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-28 09:51:34","doi":"10.21203/rs.3.rs-8701502/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":"40e2c3e4-6945-4ef1-8fdb-2fcb5c9be762","owner":[],"postedDate":"January 28th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-10T12:27:20+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-28 09:51:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8701502","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8701502","identity":"rs-8701502","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}