{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T01:42:47Z","timestamp":1775266967695,"version":"3.50.1"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T00:00:00Z","timestamp":1718323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T00:00:00Z","timestamp":1718323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Science and Engineering Research Council of Canada"},{"DOI":"10.13039\/501100020951","name":"Fonds de Recherche du Qu\u00e9bec","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100020951","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100007631","name":"Canadian Institute for Advanced Research","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007631","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s10664-024-10500-5","type":"journal-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T06:02:20Z","timestamp":1718344940000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Common challenges of deep reinforcement learning applications development: an empirical study"],"prefix":"10.1007","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7942-4791","authenticated-orcid":false,"given":"Mohammad Mehdi","family":"Morovati","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Tambon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mina","family":"Taraghi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amin","family":"Nikanjam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Foutse","family":"Khomh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,14]]},"reference":[{"issue":"2","key":"10500_CR1","first-page":"21","volume":"8","author":"M Aldhaen","year":"2020","unstructured":"Aldhaen M (2020) Interview versus questionnaire from the perspective of cbe members. Int J Educ, Learn Develop 8(2):21\u201341","journal-title":"Int J Educ, Learn Develop"},{"key":"10500_CR2","doi-asserted-by":"crossref","unstructured":"Alshangiti M, Sapkota H, Murukannaiah PK, Liu X, Yu Q (2019) Why is developing machine learning applications challenging? a study on Stack Overflow posts. In: 2019 acm\/ieee international symposium on empirical software engineering and measurement (esem). IEEE, pp 1\u201311","DOI":"10.1109\/ESEM.2019.8870187"},{"issue":"2","key":"10500_CR3","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/TITS.2020.3024655","volume":"23","author":"S Aradi","year":"2020","unstructured":"Aradi S (2020) Survey of deep reinforcement learning for motion planning of autonomous vehicles. IEEE Trans Intell Transp Syst 23(2):740\u2013759","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"10500_CR4","doi-asserted-by":"crossref","unstructured":"Arpteg A, Brinne B, Crnkovic-Friis L, Bosch J (2018) Software engineering challenges of deep learning. In: 2018 44th euromicro conference on software engineering and advanced applications (SEAA). IEEE, pp 50\u201359","DOI":"10.1109\/SEAA.2018.00018"},{"issue":"6","key":"10500_CR5","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","volume":"34","author":"K Arulkumaran","year":"2017","unstructured":"Arulkumaran K, Deisenroth MP, Brundage M, Bharath AA (2017) Deep reinforcement learning: A brief survey. IEEE Signal Process Mag 34(6):26\u201338","journal-title":"IEEE Signal Process Mag"},{"key":"10500_CR6","unstructured":"Ayman A, Aziz A, Alipour A, Laszka A (2019) Smart contract development in practice: trends, issues, and discussions on Stack Overflow. arXiv:1905.08833"},{"issue":"8","key":"10500_CR7","doi-asserted-by":"publisher","first-page":"2836","DOI":"10.1109\/TSE.2021.3070549","volume":"48","author":"M Bagherzadeh","year":"2021","unstructured":"Bagherzadeh M, Kahani N, Briand L (2021) Reinforcement learning for test case prioritization. IEEE Trans Software Eng 48(8):2836\u20132856","journal-title":"IEEE Trans Software Eng"},{"key":"10500_CR8","doi-asserted-by":"crossref","unstructured":"Bangash AA, Sahar H, Chowdhury S, Wong AW, Hindle A, Ali K (2019) What do developers know about machine learning: a study of ml discussions on stackoverflow. In: 2019 IEEE\/ACM 16th International Conference on Mining Software Repositories (MSR). IEEE, pp 260\u2013264","DOI":"10.1109\/MSR.2019.00052"},{"key":"10500_CR9","doi-asserted-by":"crossref","unstructured":"Beyer S, Macho C, Di Penta M, Pinzger M (2020) What kind of questions do developers ask on Stack Overflow? a comparison of automated approaches to classify posts into question categories. Empir Softw Eng 25:2258\u20132301","DOI":"10.1007\/s10664-019-09758-x"},{"key":"10500_CR10","unstructured":"Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, Zaremba W (2016) Openai gym"},{"key":"10500_CR11","unstructured":"Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, Zaremba W (2016) Openai gym. arXiv:1606.01540"},{"issue":"4","key":"10500_CR12","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1109\/JSTSP.2015.2400412","volume":"9","author":"JJ Bruer","year":"2015","unstructured":"Bruer JJ, Tropp JA, Cevher V, Becker SR (2015) Designing statistical estimators that balance sample size, risk, and computational cost. IEEE J Selec Topics Signal Process 9(4):612\u2013624","journal-title":"IEEE J Selec Topics Signal Process"},{"key":"10500_CR13","doi-asserted-by":"crossref","unstructured":"Cao Y, Chen L, Ma W, Li Y, Zhou Y, Wang L (2022) Towards better dependency management: A first look at dependency smells in python projects. IEEE Transactions on Software Engineering","DOI":"10.1109\/TSE.2022.3191353"},{"key":"10500_CR14","unstructured":"Castro PS, Moitra S, Gelada C, Kumar S, Bellemare MG (2018) Dopamine: A research framework for deep reinforcement learning. arXiv:1812.06110"},{"key":"10500_CR15","doi-asserted-by":"publisher","unstructured":"Chen Z, Cao Y, Liu Y, Wang H, Xie T, Liu X (2020) A comprehensive study on challenges in deploying deep learning based software. In: Proceedings of the 28th ACM joint meeting on european software engineering conference and symposium on the foundations of software engineering, ESEC\/FSE 2020. Association for Computing Machinery, New York, NY, USA , p 750\u2013762. https:\/\/doi.org\/10.1145\/3368089.3409759","DOI":"10.1145\/3368089.3409759"},{"key":"10500_CR16","doi-asserted-by":"crossref","unstructured":"de\u00a0Souza\u00a0Nascimento E, Ahmed I, Oliveira E, Palheta MP, Steinmacher I, Conte T (2019) Understanding development process of machine learning systems: Challenges and solutions. In: 2019 acm\/ieee international symposium on empirical software engineering and measurement (esem). IEEE, pp. 1\u20136","DOI":"10.1109\/ESEM.2019.8870157"},{"key":"10500_CR17","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s10664-017-9589-y","volume":"24","author":"A Decan","year":"2019","unstructured":"Decan A, Mens T, Grosjean P (2019) An empirical comparison of dependency network evolution in seven software packaging ecosystems. Empir Softw Eng 24:381\u2013416","journal-title":"Empir Softw Eng"},{"key":"10500_CR18","unstructured":"DeCarlo M (2018) Scientific inquiry in social work. Open Social Work Education"},{"key":"10500_CR19","doi-asserted-by":"publisher","first-page":"3215","DOI":"10.1007\/s10462-020-09938-y","volume":"54","author":"W Du","year":"2021","unstructured":"Du W, Ding S (2021) A survey on multi-agent deep reinforcement learning: from the perspective of challenges and applications. Artif Intell Rev 54:3215\u20133238","journal-title":"Artif Intell Rev"},{"issue":"9","key":"10500_CR20","doi-asserted-by":"publisher","first-page":"2419","DOI":"10.1007\/s10994-021-05961-4","volume":"110","author":"G Dulac-Arnold","year":"2021","unstructured":"Dulac-Arnold G, Levine N, Mankowitz DJ, Li J, Paduraru C, Gowal S, Hester T (2021) Challenges of real-world reinforcement learning: definitions, benchmarks and analysis. Mach Learn 110(9):2419\u20132468","journal-title":"Mach Learn"},{"key":"10500_CR21","unstructured":"Frost J (2019) Introduction to Statistics: An Intuitive Guide for Analyzing Data and (2019)"},{"key":"10500_CR22","doi-asserted-by":"crossref","unstructured":"Garg D, Goel P, Kandaswamy G, Ganatra A, Kotecha K (2019) A roadmap to deep learning: a state-of-the-art step towards machine learning. In: Advanced Informatics for Computing Research: Second International Conference, ICAICR 2018, Shimla, India, July 14\u201315, 2018, Revised Selected Papers, Part I 2. Springer, pp 160\u2013170","DOI":"10.1007\/978-981-13-3140-4_15"},{"key":"10500_CR23","doi-asserted-by":"crossref","unstructured":"Gibbons JD (1993) Nonparametric measures of association. 91. Sage","DOI":"10.4135\/9781412985291"},{"key":"10500_CR24","unstructured":"GoogleSheet (2020) Google: How to use google sheets. https:\/\/support.google.com\/docs\/answer\/6000292?hl=en &co=GENIE.Platform%3DDesktop. Accessed: 2023-02-01"},{"key":"10500_CR25","doi-asserted-by":"crossref","unstructured":"Hamidi A, Antoniol G, Khomh F, Di\u00a0Penta M, Hamidi M (2021) Towards understanding developers\u2019 machine-learning challenges: A multi-language study on Stack Overflow. In: 2021 IEEE 21st International Working Conference on Source Code Analysis and Manipulation (SCAM). IEEE, pp 58\u201369","DOI":"10.1109\/SCAM52516.2021.00016"},{"key":"10500_CR26","doi-asserted-by":"crossref","unstructured":"Han J, Deng S, Lo D, Zhi C, Yin J, Xia X (2020) An empirical study of the dependency networks of deep learning libraries. In: 2020 IEEE International conference on software maintenance and evolution (ICSME). IEEE, pp 868\u2013878","DOI":"10.1109\/ICSME46990.2020.00116"},{"key":"10500_CR27","doi-asserted-by":"crossref","unstructured":"Haque MU, Iwaya LH, Babar MA (2020) Challenges in docker development: A large-scale study using Stack Overflow. In: Proceedings of the 14th ACM\/IEEE International symposium on empirical software engineering and measurement (ESEM), pp 1\u201311","DOI":"10.1145\/3382494.3410693"},{"key":"10500_CR28","doi-asserted-by":"crossref","unstructured":"Heo K, Lee W, Pashakhanloo P, Naik M (2018) Effective program debloating via reinforcement learning. In: Proceedings of the 2018 ACM SIGSAC Conference on computer and communications security, pp 380\u2013394","DOI":"10.1145\/3243734.3243838"},{"key":"10500_CR29","doi-asserted-by":"crossref","unstructured":"He J, Xin Z, Xu B, Zhang T, Kim K, Yang Z, Thung F, Irsan I, Lo D (2023) Representation learning for stack overflow posts: How far are we? arXiv:2303.06853","DOI":"10.1145\/3635711"},{"key":"10500_CR30","unstructured":"Hove SE, Anda B (2005) Experiences from conducting semi-structured interviews in empirical software engineering research. In: 11th IEEE International Software Metrics Symposium (METRICS\u201905). IEEE, pp 10\u2013pp"},{"key":"10500_CR31","doi-asserted-by":"crossref","unstructured":"Huang K, Chen B, Wu S, Cao J, Ma L, Peng X (2022) Demystifying dependency bugs in deep learning stack. arXiv:2207.10347","DOI":"10.1145\/3611643.3616325"},{"key":"10500_CR32","doi-asserted-by":"crossref","unstructured":"Humbatova N, Jahangirova G, Bavota G, Riccio V, Stocco A, Tonella P (2020) Taxonomy of real faults in deep learning systems. In: Proceedings of the ACM\/IEEE 42nd International conference on software engineering, pp 1110\u20131121","DOI":"10.1145\/3377811.3380395"},{"key":"10500_CR33","doi-asserted-by":"crossref","unstructured":"Islam MJ, Nguyen G, Pan R, Rajan H (2019) A comprehensive study on deep learning bug characteristics. In: Proceedings of the 2019 27th ACM Joint meeting on european software engineering conference and symposium on the foundations of software engineering, pp 510\u2013520","DOI":"10.1145\/3338906.3338955"},{"key":"10500_CR34","doi-asserted-by":"publisher","unstructured":"Islam MJ, Pan R, Nguyen G, Rajan H (2020) Repairing deep neural networks: Fix patterns and challenges. In: Proceedings of the ACM\/IEEE 42nd International conference on software engineering, ICSE \u201920. Association for Computing Machinery, New York, NY, USA, p 1135\u20131146. https:\/\/doi.org\/10.1145\/3377811.3380378","DOI":"10.1145\/3377811.3380378"},{"key":"10500_CR35","doi-asserted-by":"publisher","first-page":"15169","DOI":"10.1007\/s11042-018-6894-4","volume":"78","author":"H Jelodar","year":"2019","unstructured":"Jelodar H, Wang Y, Yuan C, Feng X, Jiang X, Li Y, Zhao L (2019) Latent dirichlet allocation (lda) and topic modeling: models, applications, a survey. Multimedia Tools Appl 78:15169\u201315211","journal-title":"Multimedia Tools Appl"},{"issue":"6","key":"10500_CR36","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"BR Kiran","year":"2021","unstructured":"Kiran BR, Sobh I, Talpaert V, Mannion P, Al Sallab AA, Yogamani S, P\u00e9rez P (2021) Deep reinforcement learning for autonomous driving: A survey. IEEE Trans Intell Transp Syst 23(6):4909\u20134926","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"10500_CR37","unstructured":"Kuhnle A, Schaarschmidt M, Fricke K (2017) Tensorforce: a tensorflow library for applied reinforcement learning. Web page. https:\/\/github.com\/tensorforce\/tensorforce"},{"key":"10500_CR38","unstructured":"Li Y (2017) Deep reinforcement learning: An overview. arXiv:1701.07274"},{"key":"10500_CR39","unstructured":"Liang E, Liaw R, Nishihara R, Moritz P, Fox R, Goldberg K, Gonzalez J, Jordan M, Stoica I (2018) Rllib: Abstractions for distributed reinforcement learning. In: International conference on machine learning. PMLR, pp 3053\u20133062"},{"key":"10500_CR40","doi-asserted-by":"crossref","unstructured":"Lorenz U (2022) Reinforcement Learning From Scratch: Understanding Current Approaches - with Examples in Java and Greenfoot. Springer International Publishing. https:\/\/books.google.ca\/books?id=bV2YEAAAQBAJ","DOI":"10.1007\/978-3-031-09030-1"},{"key":"10500_CR41","unstructured":"Lune H, Berg BL (2017) Qualitative research methods for the social sciences. Pearson"},{"key":"10500_CR42","doi-asserted-by":"crossref","unstructured":"Lwakatare LE, Raj A, Bosch J, Olsson HH, Crnkovic I (2019) A taxonomy of software engineering challenges for machine learning systems: An empirical investigation. In: Agile processes in software engineering and extreme programming: 20th International conference, XP 2019, Montr\u00e9al, QC, Canada, May 21\u201325, 2019, Proceedings 20. Springer International Publishing, pp 227\u2013243","DOI":"10.1007\/978-3-030-19034-7_14"},{"key":"10500_CR43","doi-asserted-by":"crossref","unstructured":"McDonald N, Schoenebeck S, Forte A (2019) Reliability and inter-rater reliability in qualitative research: Norms and guidelines for cscw and hci practice. Proceedings of the ACM on human-computer interaction 3(CSCW), 1\u201323","DOI":"10.1145\/3359174"},{"issue":"7540","key":"10500_CR44","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nat 518(7540):529\u2013533","journal-title":"Nat"},{"key":"10500_CR45","unstructured":"Mojica-Hanke A, Bayona A, Linares-V\u00e1squez M, Herbold S, Gonz\u00e1lez FA (2023) What are the machine learning best practices reported by practitioners on stack exchange? arXiv:2301.10516"},{"key":"10500_CR46","unstructured":"Moritz P, Nishihara R, Wang S, Tumanov A, Liaw R, Liang E, Elibol M, Yang Z, Paul W, Jordan MI et\u00a0al (2018) Ray: A distributed framework for emerging $$\\{$$AI$$\\}$$ applications. In: 13th USENIX symposium on operating systems design and implementation (OSDI 18), pp. 561\u2013577"},{"key":"10500_CR47","doi-asserted-by":"crossref","unstructured":"Morovati MM, Nikanjam A, Khomh F, Jiang ZM (2023) Bugs in machine learning-based systems: a faultload benchmark. Empir Softw Eng 28(3):62","DOI":"10.1007\/s10664-023-10291-1"},{"key":"10500_CR48","unstructured":"Morovati, M.M., Tambon, F., Taraghi, M., Nikanjam, A., Khomh, F.: Paper replication package. https:\/\/github.com\/drlchallenges\/drl_challenges. Accessed 2023-02-01"},{"issue":"1","key":"10500_CR49","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/s10664-023-10400-0","volume":"29","author":"MM Morovati","year":"2024","unstructured":"Morovati MM, Nikanjam A, Tambon F, Khomh F, Jiang ZM (2024) Bug characterization in machine learning-based systems. Empir Softw Eng 29(1):14","journal-title":"Empir Softw Eng"},{"key":"10500_CR50","unstructured":"Nekkanti H, Reddy S (2016) Surveys in software engineering: a systematic literature review and interview study. Ph.D. thesis, MSc thesis, Blekinge Institute of Technology, Sweden"},{"issue":"10","key":"10500_CR51","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1145\/1932682.1869486","volume":"45","author":"HA Nguyen","year":"2010","unstructured":"Nguyen HA, Nguyen TT, Wilson G Jr, Nguyen AT, Kim M, Nguyen TN (2010) A graph-based approach to api usage adaptation. ACM Sigplan Notices 45(10):302\u2013321","journal-title":"ACM Sigplan Notices"},{"key":"10500_CR52","doi-asserted-by":"crossref","unstructured":"Nguyen TT, Nguyen ND, Nahavandi S (2020) Deep reinforcement learning for multiagent systems: a review of challenges, solutions, and applications. IEEE Transactions on Cybernetics 50(9):3826\u20133839","DOI":"10.1109\/TCYB.2020.2977374"},{"issue":"1","key":"10500_CR53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3470006","volume":"31","author":"A Nikanjam","year":"2021","unstructured":"Nikanjam A, Braiek HB, Morovati MM, Khomh F (2021) Automatic fault detection for deep learning programs using graph transformations. ACM Transactions on Software Engineering and Methodology (TOSEM) 31(1):1\u201327","journal-title":"ACM Transactions on Software Engineering and Methodology (TOSEM)"},{"issue":"1","key":"10500_CR54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10515-021-00313-x","volume":"29","author":"A Nikanjam","year":"2022","unstructured":"Nikanjam A, Morovati MM, Khomh F, Ben Braiek H (2022) Faults in deep reinforcement learning programs: a taxonomy and a detection approach. Autom Softw Eng 29(1):1\u201332","journal-title":"Autom Softw Eng"},{"key":"10500_CR55","doi-asserted-by":"crossref","unstructured":"Openja M, Majidi F, Khomh F, Chembakottu B, Li H (2022) Studying the practices of deploying machine learning projects on docker. In: Proceedings of the 26th International conference on evaluation and assessment in software engineering, pp 190\u2013200","DOI":"10.1145\/3530019.3530039"},{"key":"10500_CR56","doi-asserted-by":"crossref","unstructured":"Panerati J, Zheng H, Zhou S, Xu J, Prorok A, Schoellig AP (2021) Learning to fly\u2013a gym environment with pybullet physics for reinforcement learning of multi-agent quadcopter control. In: 2021 IEEE\/RSJ International conference on intelligent robots and systems (IROS). IEEE, pp 7512\u20137519","DOI":"10.1109\/IROS51168.2021.9635857"},{"issue":"13","key":"10500_CR57","doi-asserted-by":"publisher","first-page":"4316","DOI":"10.1080\/00207543.2021.1973138","volume":"60","author":"M Panzer","year":"2022","unstructured":"Panzer M, Bender B (2022) Deep reinforcement learning in production systems: a systematic literature review. Int J Prod Res 60(13):4316\u20134341","journal-title":"Int J Prod Res"},{"key":"10500_CR58","doi-asserted-by":"crossref","unstructured":"Peruma A, Simmons S, AlOmar EA, Newman CD, Mkaouer MW, Ouni A (2022) How do i refactor this? an empirical study on refactoring trends and topics in Stack Overflow. Empir Softw Eng 27(1):11","DOI":"10.1007\/s10664-021-10045-x"},{"key":"10500_CR59","unstructured":"Plappert M (2016) keras-rl. https:\/\/github.com\/keras-rl\/keras-rl"},{"key":"10500_CR60","unstructured":"Pumperla M, Oakes E, Liaw R (2023) Learning ray: flexible distributed python for machine learning. O\u2019Reilly media. https:\/\/books.google.ca\/books?id=vKj0zgEACAAJ"},{"key":"10500_CR61","unstructured":"Qualtrics (2023) Qualtrics official website. https:\/\/www.qualtrics.com\/. Accessed 04 Jan 2023"},{"key":"10500_CR62","doi-asserted-by":"crossref","unstructured":"Rao Q, Frtunikj J (2018) Deep learning for self-driving cars: chances and challenges. In: Proceedings of the 1st international workshop on software engineering for AI in autonomous systems, pp 35\u201338","DOI":"10.1145\/3194085.3194087"},{"key":"10500_CR63","doi-asserted-by":"crossref","unstructured":"Reda D, Tao T, van\u00a0de Panne M (2020) Learning to locomote: understanding how environment design matters for deep reinforcement learning. In: Proceedings of the 13th ACM SIGGRAPH conference on motion, interaction and games, pp 1\u201310","DOI":"10.1145\/3424636.3426907"},{"key":"10500_CR64","unstructured":"Schaarschmidt M, Kuhnle A, Ellis B, Fricke K, Gessert F, Yoneki E (2018) LIFT: reinforcement learning in computer systems by learning from demonstrations. http:\/\/arxiv.org\/abs\/1808.07903"},{"key":"10500_CR65","doi-asserted-by":"crossref","unstructured":"Schoop E, Huang F, Hartmann B (2021) Umlaut: debugging deep learning programs using program structure and model behavior. In: Proceedings of the 2021 CHI conference on human factors in computing systems, pp 1\u201316","DOI":"10.1145\/3411764.3445538"},{"key":"10500_CR66","unstructured":"Shah MB, Rahman MM, Khomh F (2024) Towards enhancing the reproducibility of deep learning bugs: an empirical study. arXiv:2401.03069"},{"key":"10500_CR67","unstructured":"StackExchange (2022) Stack exchange data dump. https:\/\/archive.org\/details\/stackexchange. Accessed 02 Jan 2023"},{"key":"10500_CR68","doi-asserted-by":"crossref","unstructured":"Tambon F, Majdinasab V, Nikanjam A, Khomh F, Antoniol G (2023) Mutation testing of deep reinforcement learning based on real faults. In: 2023 IEEE Conference on software testing, verification and validation (ICST). IEEE, pp 188\u2013198","DOI":"10.1109\/ICST57152.2023.00026"},{"key":"10500_CR69","unstructured":"Vijayaraghavan G, Kaner C (2003) Bug taxonomies: use them to generate better tests. Star East 2003:1\u201340"},{"key":"10500_CR70","doi-asserted-by":"crossref","unstructured":"Wan Y, Zhao Z, Yang M, Xu G, Ying H, Wu J, Yu PS (2018) Improving automatic source code summarization via deep reinforcement learning. In: Proceedings of the 33rd ACM\/IEEE international conference on automated software engineering, pp 397\u2013407","DOI":"10.1145\/3238147.3238206"},{"key":"10500_CR71","doi-asserted-by":"crossref","unstructured":"Xiao Y, Liu J, Wu J, Ansari N (2021) Leveraging deep reinforcement learning for traffic engineering: a survey. IEEE Commun Surv Tutor 23(4):2064\u20132097","DOI":"10.1109\/COMST.2021.3102580"},{"key":"10500_CR72","doi-asserted-by":"crossref","unstructured":"Xie D, Li Y, Kim M, Pham HV, Tan L, Zhang X, Godfrey MW (2022) Docter: documentation-guided fuzzing for testing deep learning api functions. In: Proceedings of the 31st ACM SIGSOFT international symposium on software testing and analysis, pp 176\u2013188","DOI":"10.1145\/3533767.3534220"},{"key":"10500_CR73","doi-asserted-by":"crossref","unstructured":"Yahmed AH, Abbassi AA, Nikanjam A, Li H, Khomh F (2023) Deploying deep reinforcement learning systems: a taxonomy of challenges. arXiv:2308.12438","DOI":"10.1109\/ICSME58846.2023.00015"},{"key":"10500_CR74","doi-asserted-by":"crossref","unstructured":"Yu C, Liu J, Nemati S, Yin G (2021) Reinforcement learning in healthcare: a survey. ACM Comput Surv (CSUR) 55(1):1\u201336","DOI":"10.1145\/3477600"},{"key":"10500_CR75","doi-asserted-by":"crossref","unstructured":"Zahedi M, Rajapakse RN, Babar MA (2020) Mining questions asked about continuous software engineering: a case study of Stack Overflow. In: Proceedings of the evaluation and assessment in software engineering, pp 41\u201350","DOI":"10.1145\/3383219.3383224"},{"key":"10500_CR76","volume-title":"Deep Reinforcement Learning: Fundamentals","author":"S Zhang","year":"2020","unstructured":"Zhang S, Ding Z, Dong H (2020) Deep Reinforcement Learning: Fundamentals. Springer, Research and Applications"},{"key":"10500_CR77","doi-asserted-by":"crossref","unstructured":"Zhang T, Gao C, Ma L, Lyu M, Kim M (2019) An empirical study of common challenges in developing deep learning applications. In: 2019 IEEE 30th International Symposium on Software Reliability Engineering (ISSRE). IEEE, pp 104\u2013115","DOI":"10.1109\/ISSRE.2019.00020"},{"key":"10500_CR78","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhai J, Ma S, Shen C (2021) Autotrainer: an automatic dnn training problem detection and repair system. In: 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE). IEEE, pp 359\u2013371","DOI":"10.1109\/ICSE43902.2021.00043"},{"issue":"6","key":"10500_CR79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10664-022-10180-z","volume":"27","author":"W Zhu","year":"2022","unstructured":"Zhu W, Zhang H, Hassan AE, Godfrey MW (2022) An empirical study of question discussions on stack overflow. Empir Softw Eng 27(6):1\u201325","journal-title":"Empir Softw Eng"},{"key":"10500_CR80","doi-asserted-by":"crossref","unstructured":"Zolfagharian A, Abdellatif M, Briand L, Bagherzadeh M et\u00a0al (2022) Search-based testing approach for deep reinforcement learning agents. arXiv:2206.07813","DOI":"10.1109\/TSE.2023.3269804"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-024-10500-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-024-10500-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-024-10500-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T15:21:54Z","timestamp":1720192914000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-024-10500-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,14]]},"references-count":80,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["10500"],"URL":"https:\/\/doi.org\/10.1007\/s10664-024-10500-5","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,14]]},"assertion":[{"value":"17 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest. The authors have no competing interests to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"95"}}