{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T19:42:41Z","timestamp":1783194161955,"version":"3.54.6"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T00:00:00Z","timestamp":1639958400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T00:00:00Z","timestamp":1639958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002790","name":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002790","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008240","name":"Fonds de Recherche du Qu\u00e9bec-Soci\u00e9t\u00e9 et Culture","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008240","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Autom Softw Eng"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s10515-021-00313-x","type":"journal-article","created":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T08:04:52Z","timestamp":1639987492000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Faults in deep reinforcement learning programs: a taxonomy and a detection approach"],"prefix":"10.1007","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0440-6839","authenticated-orcid":false,"given":"Amin","family":"Nikanjam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad Mehdi","family":"Morovati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Foutse","family":"Khomh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houssem","family":"Ben Braiek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,12,20]]},"reference":[{"key":"313_CR1","doi-asserted-by":"crossref","unstructured":"Agostinelli, F., Hocquet, G., Singh, S., Baldi, P.: From reinforcement learning to deep reinforcement learning: An overview. In: Braverman Readings in Machine Learning. Key Ideas From Inception to Current State, pp. 298\u2013328. Springer (2018)","DOI":"10.1007\/978-3-319-99492-5_13"},{"key":"313_CR2","unstructured":"Akkaya, I., Andrychowicz, M., Chociej, M., Litwin, M., McGrew, B., Petron, A., Paino, A., Plappert, M., Powell, G., Ribas, R., et\u00a0al.: Solving rubik\u2019s cube with a robot hand. arXiv preprint arXiv:1910.07113 (2019)"},{"key":"313_CR3","doi-asserted-by":"crossref","unstructured":"Bagherzadeh, M., Khatchadourian, R.: Going big: a large-scale study on what big data developers ask. In: Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 432\u2013442 (2019)","DOI":"10.1145\/3338906.3338939"},{"issue":"7836","key":"313_CR4","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1038\/s41586-020-2939-8","volume":"588","author":"MG Bellemare","year":"2020","unstructured":"Bellemare, M.G., Candido, S., Castro, P.S., Gong, J., Machado, M.C., Moitra, S., Ponda, S.S., Wang, Z.: Autonomous navigation of stratospheric balloons using reinforcement learning. Nature 588(7836), 77\u201382 (2020)","journal-title":"Nature"},{"key":"313_CR5","doi-asserted-by":"crossref","unstructured":"Borges, H., Hora, A., Valente, M.T.: Understanding the factors that impact the popularity of github repositories. In: 2016 IEEE International Conference on Software Maintenance and Evolution (ICSME), pp. 334\u2013344. IEEE (2016)","DOI":"10.1109\/ICSME.2016.31"},{"key":"313_CR6","unstructured":"Castro, P.S., Moitra, S., Gelada, C., Kumar, S., Bellemare, M.G.: Dopamine: A Research Framework for Deep Reinforcement Learning. arXiv:1812.06110 (2018)"},{"key":"313_CR7","unstructured":"Fischer, T.G.: Reinforcement learning in financial markets-a survey. Tech. rep., FAU Discussion Papers in Economics (2018)"},{"key":"313_CR8","doi-asserted-by":"crossref","unstructured":"Fran\u00e7ois-Lavet, V., Henderson, P., Islam, R., Bellemare, M.G., Pineau, J.: An Introduction to Deep Reinforcement Learning, vol.\u00a011 (2018)","DOI":"10.1561\/9781680835397"},{"key":"313_CR9","doi-asserted-by":"crossref","unstructured":"Gandhi, D., Pinto, L., Gupta, A.: Learning to fly by crashing. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3948\u20133955. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206247"},{"issue":"1","key":"313_CR10","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/s10009-011-0186-x","volume":"14","author":"AH Ghamarian","year":"2012","unstructured":"Ghamarian, A.H., de Mol, M., Rensink, A., Zambon, E., Zimakova, M.: Modelling and analysis using groove. Int. J. Softw. Tools Technol. Transf. 14(1), 15\u201340 (2012)","journal-title":"Int. J. Softw. Tools Technol. Transf."},{"key":"313_CR12","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016) http:\/\/www.deeplearningbook.org"},{"key":"313_CR14","doi-asserted-by":"crossref","unstructured":"Hartmann, T., Moawad, A., Schockaert, C., Fouquet, F., Le\u00a0Traon, Y.: Meta-modelling meta-learning. In: 2019 ACM\/IEEE 22nd International Conference on Model Driven Engineering Languages and Systems (MODELS), pp. 300\u2013305. IEEE (2019)","DOI":"10.1109\/MODELS.2019.00014"},{"issue":"1","key":"313_CR15","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.entcs.2005.12.018","volume":"148","author":"R Heckel","year":"2006","unstructured":"Heckel, R.: Graph transformation in a nutshell. Electron. Notes Theor. Comput. Sci. 148(1), 187\u2013198 (2006)","journal-title":"Electron. Notes Theor. Comput. Sci."},{"key":"313_CR16","doi-asserted-by":"crossref","unstructured":"Humbatova, N., Jahangirova, G., Bavota, G., Riccio, V., Stocco, A., Tonella, P.: Taxonomy of real faults in deep learning systems. In: The 42nd International Conference on Software Engineering (ICSE 2020). ACM (2020)","DOI":"10.1145\/3377811.3380395"},{"key":"313_CR17","doi-asserted-by":"crossref","unstructured":"Islam, M.J., Nguyen, G., Pan, R., Rajan, H.: 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 (2019)","DOI":"10.1145\/3338906.3338955"},{"key":"313_CR18","doi-asserted-by":"crossref","unstructured":"Islam, M.J., Pan, R., Nguyen, G., Rajan, H.: Repairing deep neural networks: Fix patterns and challenges. In: 2020 IEEE\/ACM 42nd International Conference on Software Engineering (ICSE), pp. 1135\u20131146. IEEE (2020)","DOI":"10.1145\/3377811.3380378"},{"key":"313_CR19","unstructured":"Kuhnle, A., Schaarschmidt, M., Fricke, K.: Tensorforce: a tensorflow library for applied reinforcement learning. https:\/\/github.com\/tensorforce\/tensorforce (2017)"},{"key":"313_CR20","volume-title":"Deep Reinforcement Learning Hands-On: Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO","author":"M Lapan","year":"2018","unstructured":"Lapan, M.: Deep Reinforcement Learning Hands-On: Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO. Packt Publishing Ltd, AlphaGo Zero and more (2018)"},{"issue":"1","key":"313_CR21","first-page":"1334","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(1), 1334\u20131373 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"313_CR22","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"313_CR23","doi-asserted-by":"crossref","unstructured":"Meldrum, S., Licorish, S.A., Savarimuthu, B.T.R.: Crowdsourced knowledge on stack overflow: A systematic mapping study. In: Proceedings of the 21st International Conference on Evaluation and Assessment in Software Engineering, pp. 180\u2013185 (2017)","DOI":"10.1145\/3084226.3084267"},{"key":"313_CR24","unstructured":"Mnih, V., Badia, A.P., Mirza, M., Graves, A., Lillicrap, T., Harley, T., Silver, D., Kavukcuoglu, K.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"issue":"7540","key":"313_CR25","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, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"313_CR26","volume-title":"Grokking Deep Reinforcement Learning","author":"M Morales","year":"2019","unstructured":"Morales, M.: Grokking Deep Reinforcement Learning. Manning Publications, New York (2019)"},{"issue":"6337","key":"313_CR27","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1126\/science.aam6960","volume":"356","author":"M Morav\u010d\u00edk","year":"2017","unstructured":"Morav\u010d\u00edk, M., Schmid, M., Burch, N., Lis\u1ef3, V., Morrill, D., Bard, N., Davis, T., Waugh, K., Johanson, M., Bowling, M.: Deepstack: Eepert-level artificial intelligence in heads-up no-limit poker. Science 356(6337), 508\u2013513 (2017)","journal-title":"Science"},{"key":"313_CR30","unstructured":"Plappert, M.: keras-rl. https:\/\/github.com\/keras-rl\/keras-rl (2016)"},{"key":"313_CR32","first-page":"479","volume-title":"International Workshop on Applications of Graph Transformations with Industrial Relevance","author":"A Rensink","year":"2003","unstructured":"Rensink, A.: The GROOVE simulator: A tool for state space generation. In: International Workshop on Applications of Graph Transformations with Industrial Relevance, pp. 479\u2013485. Springer, Berlin (2003)"},{"issue":"19","key":"313_CR33","doi-asserted-by":"publisher","first-page":"70","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023","volume":"2017","author":"AE Sallab","year":"2017","unstructured":"Sallab, A.E., Abdou, M., Perot, E., Yogamani, S.: Deep reinforcement learning framework for autonomous driving. Electron. Imag. 2017(19), 70\u201376 (2017)","journal-title":"Electron. Imag."},{"issue":"7839","key":"313_CR34","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., Antonoglou, I., Hubert, T., Simonyan, K., Sifre, L., Schmitt, S., Guez, A., Lockhart, E., Hassabis, D., Graepel, T., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","journal-title":"Nature"},{"issue":"4","key":"313_CR35","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1109\/32.799955","volume":"25","author":"CB Seaman","year":"1999","unstructured":"Seaman, C.B.: Qualitative methods in empirical studies of software engineering. IEEE Trans. Softw. Eng. 25(4), 557\u2013572 (1999)","journal-title":"IEEE Trans. Softw. Eng."},{"issue":"7587","key":"313_CR36","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"313_CR37","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"313_CR41","doi-asserted-by":"crossref","unstructured":"Trujillo, M., Linares-V\u00e1squez, M., Escobar-Vel\u00e1squez, C., Dusparic, I., Cardozo, N.: Does neuron coverage matter for deep reinforcement learning? a preliminary study. In: DeepTest Workshop, ICSE 2020 (2020)","DOI":"10.1145\/3387940.3391462"},{"key":"313_CR42","first-page":"1","volume":"2003","author":"G Vijayaraghavan","year":"2003","unstructured":"Vijayaraghavan, G., Kaner, C.: Bug taxonomies: use them to generate better tests. Star East 2003, 1\u201340 (2003)","journal-title":"Star East"},{"issue":"3\u20134","key":"313_CR43","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"313_CR44","unstructured":"Yu, C., Liu, J., Nemati, S.: Reinforcement learning in healthcare: a survey. arXiv preprint arXiv:1908.08796 (2019)"},{"key":"313_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, Y., Cheung, S.C., Xiong, Y., Zhang, L.: An empirical study on tensorflow program bugs. In: Proceedings of the 27th ACM SIGSOFT International Symposium on Software Testing and Analysis, pp. 129\u2013140 (2018)","DOI":"10.1145\/3213846.3213866"},{"key":"313_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, T., Gao, C., Ma, L., Lyu, M.R., Kim, M.: An empirical study of common challenges in developing deep learning applications. In: The 30th IEEE International Symposium on Software Reliability Engineering (ISSRE) (2019)","DOI":"10.1109\/ISSRE.2019.00020"},{"key":"313_CR47","unstructured":"Zhang, B., Rajan, R., Pineda, L., Lambert, N., Biedenkapp, A., Chua, K., Hutter, F., Calandra, R.: On the importance of hyperparameter optimization for model-based reinforcement learning. In: International Conference on Artificial Intelligence and Statistics, pp. 4015\u20134023. PMLR (2021)"}],"container-title":["Automated Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-021-00313-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10515-021-00313-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-021-00313-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T15:34:19Z","timestamp":1650900859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10515-021-00313-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,20]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["313"],"URL":"https:\/\/doi.org\/10.1007\/s10515-021-00313-x","relation":{},"ISSN":["0928-8910","1573-7535"],"issn-type":[{"value":"0928-8910","type":"print"},{"value":"1573-7535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,20]]},"assertion":[{"value":"31 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"8"}}