{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T21:24:14Z","timestamp":1758057854896,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051875","type":"print"},{"value":"9783032051882","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-05188-2_9","type":"book-chapter","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T21:52:55Z","timestamp":1757973175000},"page":"125-141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reusable Test Suites for\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2201-997X","authenticated-orcid":false,"given":"J\u00f8rn Eirik","family":"Betten","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3519-5514","authenticated-orcid":false,"given":"Quentin","family":"Mazouni","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5734-0538","authenticated-orcid":false,"given":"Dennis","family":"Gross","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8176-666X","authenticated-orcid":false,"given":"Pedro","family":"Lind","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2494-4279","authenticated-orcid":false,"given":"Helge","family":"Spieker","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S.: Safe reinforcement learning via shielding (2017). arXiv:1708.08611","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Biagiola, M., Tonella, P.: Testing of deep reinforcement learning agents with surrogate models. ACM Trans. Softw. Eng. Methodol. 33(3), 73:1\u201373:33 (2024)","DOI":"10.1145\/3631970"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Birchler, C., Khatiri, S., Derakhshanfar, P., Panichella, S., Panichella, A.: Single and multi-objective test cases prioritization for self-driving cars in virtual environments. ACM Trans. Softw. Eng. Methodol. 32(2), 28:1\u201328:30 (2023)","DOI":"10.1145\/3533818"},{"issue":"2","key":"9_CR4","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1109\/4235.996017","volume":"6","author":"K Deb","year":"2002","unstructured":"Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182\u2013197 (2002)","journal-title":"IEEE Trans. Evol. Comput."},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Eisenhut, J., Torralba, A., Christakis, M., Hoffmann, J.: Automatic metamorphic test oracles for action-policy testing. In: Proceedings of the International Conference on Automated Planning and Scheduling, vol. 33, pp. 109\u2013117 (2023)","DOI":"10.1609\/icaps.v33i1.27185"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Fang, M., Wang, X., Gong, N.Z.: Provably robust federated reinforcement learning (2025). arXiv:2502.08123","DOI":"10.1145\/3696410.3714728"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Gross, D., Jansen, N., Junges, S., P\u00e9rez, G.A.: COOL-MC: a comprehensive tool for reinforcement learning and model checking. In: Dependable Software Engineering. Theories, Tools, and Applications: International Symposium, SETTA (2022)","DOI":"10.1007\/978-3-031-21213-0_3"},{"key":"9_CR8","unstructured":"Koyamada, S., et al.: PGX: Hardware-accelerated Parallel Game simulators for reinforcement learning. Adv. Neural. Inf. Process. Syst. 36, 45716\u201345743 (2023)"},{"issue":"1","key":"9_CR9","doi-asserted-by":"publisher","DOI":"10.1002\/stvr.1864","volume":"34","author":"Y Li","year":"2024","unstructured":"Li, Y., Wang, Z., Wang, J., Chen, J., Mou, R., Li, G.: Semantic-aware Two-phase Test Case Prioritization for Continuous Integration. Softw. Test. Verificat. Reliabil. 34(1), e1864 (2024)","journal-title":"Softw. Test. Verificat. Reliabil."},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Generative model-based testing on decision-making policies. In: 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE), pp. 243\u2013254 (2023). iSSN: 2643-1572","DOI":"10.1109\/ASE56229.2023.00153"},{"issue":"01","key":"9_CR11","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/TSE.2024.3491193","volume":"51","author":"X Ma","year":"2025","unstructured":"Ma, X., et al.: Diversity-oriented Testing for Competitive Game Agent via Constraint-guided Adversarial Agent Training. IEEE Trans. Softw. Eng. 51(01), 66\u201381 (2025)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Mazouni, Q., Spieker, H., Gotlieb, A., Acher, M.: Testing for fault diversity in reinforcement learning. In: Proceedings of the 5th ACM\/IEEE International Conference on Automation of Software Test (AST) (2024)","DOI":"10.1145\/3644032.3644458"},{"key":"9_CR13","doi-asserted-by":"publisher","unstructured":"Milani, S., Topin, N., Veloso, M., Fang, F.: Explainable reinforcement learning: a survey and comparative review. ACM Comput. Surv. 56(7), 168:1\u2013168:36 (2024). https:\/\/doi.org\/10.1145\/3616864","DOI":"10.1145\/3616864"},{"key":"9_CR14","unstructured":"Molnar, C.: Interpretable Machine Learning - A Guide for Making Black-Box Models Explainable, 3 edn. Christoph Molnar (2025)"},{"key":"9_CR15","unstructured":"Mouret, J.B., Clune, J.: Illuminating search spaces by mapping elites. ArXiv (2015)"},{"key":"9_CR16","unstructured":"NVIDIA: NVIDIA Announces Isaac GR00T N1\u2014the World\u2019s First Open Humanoid Robot Foundation Model\u2014and Simulation Frameworks to Speed Robot Development (2025)"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Pang, Q., Yuan, Y., Wang, S.: MDPFuzz: testing models solving markov decision processes (2023). arXiv:2112.02807","DOI":"10.1145\/3533767.3534388"},{"key":"9_CR18","first-page":"28103","volume":"37","author":"S Pranger","year":"2024","unstructured":"Pranger, S., Chockler, H., Tappler, M., K\u00f6nighofer, B.: Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning. Adv. Neural. Inf. Process. Syst. 37, 28103\u201328126 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR19","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017). arXiv:1707.06347"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Shi, A., Yung, T., Gyori, A., Marinov, D.: Comparing and combining test-suite reduction and regression test selection. In: Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering, ESEC\/FSE 2015, pp. 237\u2013247. Association for Computing Machinery, New York (2015)","DOI":"10.1145\/2786805.2786878"},{"issue":"1\u20132","key":"9_CR21","doi-asserted-by":"publisher","DOI":"10.1002\/stvr.1695","volume":"29","author":"D Shin","year":"2019","unstructured":"Shin, D., Yoo, S., Papadakis, M., Bae, D.H.: Empirical Evaluation of Mutation-based Test Case Prioritization Techniques. Softw. Test. Verificat. Reliabil. 29(1\u20132), e1695 (2019)","journal-title":"Softw. Test. Verificat. Reliabil."},{"issue":"7587","key":"9_CR22","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the Game of Go with Deep Neural Networks and Tree Search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Spieker, H., Gotlieb, A., Marijan, D., Mossige, M.: Reinforcement learning for automatic test case prioritization and selection in continuous integration. In: Proceedings of the 26th ACM SIGSOFT International Symposium on Software Testing and Analysis (2017)","DOI":"10.1145\/3092703.3092709"},{"key":"9_CR24","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2015","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press, Cambridge (2015)","edition":"2"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Tappler, M., C\u00f3rdoba, F.C., Aichernig, B.K., K\u00f6nighofer, B.: Search-based testing of reinforcement learning (2022). arXiv:2205.04887","DOI":"10.24963\/ijcai.2022\/72"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Ul\u00a0Haq, F., Shin, D., Briand, L.C.: Many-objective reinforcement learning for online testing of DNN-enabled systems. In: 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE), pp. 1814\u20131826 (2023). iSSN: 1558-1225","DOI":"10.1109\/ICSE48619.2023.00155"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Vouros, G.A.: Explainable deep reinforcement learning: state of the art and challenges. ACM Comput. Surv. 55(5), 1\u201339 (2023). arXiv:2301.09937","DOI":"10.1145\/3527448"},{"key":"9_CR28","unstructured":"Waymo: Why you\u2019ll hear us saying fully autonomous driving tech from now on (2021)"},{"key":"9_CR29","unstructured":"Young, K., Tian, T.: MinAtar: an atari-inspired testbed for thorough and reproducible reinforcement learning experiments (2019). arXiv:1903.03176"},{"issue":"07","key":"9_CR30","doi-asserted-by":"publisher","first-page":"3715","DOI":"10.1109\/TSE.2023.3269804","volume":"49","author":"A Zolfagharian","year":"2023","unstructured":"Zolfagharian, A., Abdellatif, M., Briand, L.C., Bagherzadeh, M.: A Search-based Testing Approach for Deep Reinforcement Learning Agents. IEEE Trans. Softw. Eng. 49(07), 3715\u20133735 (2023)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Zolfagharian, A., Abdellatif, M., Briand, L.C., S, R.: SMARLA: a safety monitoring approach for deep reinforcement learning agents (2024). arXiv:2308.02594","DOI":"10.1145\/3639478.3643072"}],"container-title":["Lecture Notes in Computer Science","Testing Software and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05188-2_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T21:53:02Z","timestamp":1757973182000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05188-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032051875","9783032051882"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05188-2_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"16 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICTSS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Testing Software and Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"37","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pts2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conf.researchr.org\/home\/ictss-2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}