{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T21:09:36Z","timestamp":1788728976727,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376695","type":"print"},{"value":"9783032376701","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-37670-1_23","type":"book-chapter","created":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:43:23Z","timestamp":1788727403000},"page":"393-410","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Framework"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-4186","authenticated-orcid":false,"given":"Chengpeng","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5073-0787","authenticated-orcid":false,"given":"Yingqian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7211-8070","authenticated-orcid":false,"given":"Hendrik","family":"Baier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"issue":"3","key":"23_CR1","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1287\/mnsc.34.3.391","volume":"34","author":"J Adams","year":"1988","unstructured":"Adams, J., Balas, E., Zawack, D.: The shifting bottleneck procedure for job shop scheduling. Manage. Sci. 34(3), 391\u2013401 (1988)","journal-title":"Manage. Sci."},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Aleixo, D.S., Lelis, L.H.: Show me the way! Bilevel search for synthesizing programmatic strategies. In: the AAAI Conference on Artificial Intelligence, vol. 37, pp. 4991\u20134998 (2023)","DOI":"10.1609\/aaai.v37i4.25626"},{"issue":"2","key":"23_CR3","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1287\/ijoc.3.2.149","volume":"3","author":"D Applegate","year":"1991","unstructured":"Applegate, D., Cook, W.: A computational study of the job-shop scheduling problem. ORSA J. Comput. 3(2), 149\u2013156 (1991)","journal-title":"ORSA J. Comput."},{"key":"23_CR4","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"AB Arrieta","year":"2020","unstructured":"Arrieta, A.B., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. fusion 58, 82\u2013115 (2020)","journal-title":"Inf. fusion"},{"key":"23_CR5","unstructured":"Carvalho, T.H., Tjhia, K., Lelis, L.: Reclaiming the source of programmatic policies: programmatic versus latent spaces. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=NGVljI6HkR"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Choi, D., Langley, P.: Learning teleoreactive logic programs from problem solving. In: International Conference on Inductive Logic Programming, pp. 51\u201368 (2005)","DOI":"10.1007\/11536314_4"},{"key":"23_CR7","doi-asserted-by":"publisher","first-page":"105528","DOI":"10.52202\/079017-3349","volume":"37","author":"A Corsini","year":"2024","unstructured":"Corsini, A., Porrello, A., Calderara, S., Dell\u2019Amico, M.: Self-labeling the job shop scheduling problem. Adv. Neural. Inf. Process. Syst. 37, 105528\u2013105551 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"23_CR8","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/S0377-2217(97)00019-2","volume":"109","author":"E Demirkol","year":"1998","unstructured":"Demirkol, E., Mehta, S., Uzsoy, R.: Benchmarks for shop scheduling problems. Eur. J. Oper. Res. 109(1), 137\u2013141 (1998)","journal-title":"Eur. J. Oper. Res."},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Dwivedi, R., et al.: Explainable AI (XAI): core ideas, techniques, and solutions. ACM Comput. Surv. 55(9), 194:1\u2013194:33 (2023)","DOI":"10.1145\/3561048"},{"key":"23_CR10","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1007\/s00170-005-0190-y","volume":"31","author":"A El-Bouri","year":"2006","unstructured":"El-Bouri, A., Shah, P.: A neural network for dispatching rule selection in a job shop. Int. J. Adv. Manuf. Technol. 31, 342\u2013349 (2006)","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"23_CR11","unstructured":"Fisher, H., Thompson, G.: Probabilistic learning combinations of local job-shop scheduling rules. In: Industrial Scheduling, pp. 225\u2013251 (1963)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Gu, Y., Zhang, K., Liu, Q., Gao, W., Li, L., Zhou, J.: $$\\pi $$-light: programmatic interpretable reinforcement learning for resource-limited traffic signal control. In: the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 21107\u201321115 (2024)","DOI":"10.1609\/aaai.v38i19.30103"},{"key":"23_CR13","doi-asserted-by":"publisher","first-page":"109255","DOI":"10.1016\/j.cie.2023.109255","volume":"180","author":"Y Gui","year":"2023","unstructured":"Gui, Y., Tang, D., Zhu, H., Zhang, Y., Zhang, Z.: Dynamic scheduling for flexible job shop using a deep reinforcement learning approach. Comput. Industr. Eng. 180, 109255 (2023)","journal-title":"Comput. Industr. Eng."},{"key":"23_CR14","doi-asserted-by":"publisher","first-page":"186474","DOI":"10.1109\/ACCESS.2020.3029868","volume":"8","author":"BA Han","year":"2020","unstructured":"Han, B.A., Yang, J.J.: Research on adaptive job shop scheduling problems based on dueling double DQN. IEEE Access 8, 186474\u2013186495 (2020)","journal-title":"IEEE Access"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Haupt, R.: A survey of priority rule-based scheduling. Oper.-Res.-Spektr. 11(1), 3\u201316 (1989)","DOI":"10.1007\/BF01721162"},{"issue":"10","key":"23_CR16","doi-asserted-by":"publisher","first-page":"19327","DOI":"10.1109\/TNNLS.2025.3582299","volume":"36","author":"C Hu","year":"2025","unstructured":"Hu, C., Wang, Z., Yuan, B., Liu, J., Zhang, C., Yao, X.: Robust dynamic material handling via adaptive constrained evolutionary reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. 36(10), 19327\u201319341 (2025). https:\/\/doi.org\/10.1109\/TNNLS.2025.3582299","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"23_CR17","unstructured":"Lawrence, S.: Resouce constrained project scheduling: an experimental investigation of heuristic scheduling techniques (supplement). Graduate School of Industrial Administration, Carnegie-Mellon University (1984)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Logic-Q: improving deep reinforcement learning-based quantitative trading via program sketch-based tuning. In: the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 18584\u201318592 (2025)","DOI":"10.1609\/aaai.v39i17.34045"},{"key":"23_CR19","doi-asserted-by":"publisher","first-page":"126677","DOI":"10.52202\/079017-4024","volume":"37","author":"YA Lin","year":"2024","unstructured":"Lin, Y.A., Lee, C.T., Yang, C.H., Liu, G.T., Sun, S.H.: Hierarchical programmatic option framework. Adv. Neural. Inf. Process. Syst. 37, 126677\u2013126724 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR20","doi-asserted-by":"publisher","first-page":"106208","DOI":"10.1016\/j.asoc.2020.106208","volume":"91","author":"S Luo","year":"2020","unstructured":"Luo, S.: Dynamic scheduling for flexible job shop with new job insertions by deep reinforcement learning. Appl. Soft Comput. 91, 106208 (2020)","journal-title":"Appl. Soft Comput."},{"key":"23_CR21","doi-asserted-by":"publisher","first-page":"107489","DOI":"10.1016\/j.cie.2021.107489","volume":"159","author":"S Luo","year":"2021","unstructured":"Luo, S., Zhang, L., Fan, Y.: Dynamic multi-objective scheduling for flexible job shop by deep reinforcement learning. Comput. Industr. Eng. 159, 107489 (2021)","journal-title":"Comput. Industr. Eng."},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Marino, J.R., Moraes, R.O., Oliveira, T.C., Toledo, C., Lelis, L.H.: Programmatic strategies for real-time strategy games. In: the AAAI Conference on Artificial Intelligence, vol. 35, pp. 381\u2013389 (2021)","DOI":"10.1609\/aaai.v35i1.16114"},{"issue":"7","key":"23_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3616864","volume":"56","author":"S Milani","year":"2024","unstructured":"Milani, S., Topin, N., Veloso, M., Fang, F.: Explainable reinforcement learning: a survey and comparative review. ACM Comput. Surv. 56(7), 1\u201336 (2024)","journal-title":"ACM Comput. Surv."},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Moraes, R.O., Asif Sadmine, Q., Baier, H., Lelis, L.H.S.: InnateCoder: learning programmatic options with foundation models. In: Thirty-Fourth International Joint Conference on Artificial Intelligence, pp. 7652\u20137660 (2025)","DOI":"10.24963\/ijcai.2025\/851"},{"key":"23_CR25","unstructured":"Moraes, R.O., Lelis, L.H.: Searching for programmatic policies in semantic spaces. In: the International Joint Conference on Artificial Intelligence, pp. 5990\u20135998 (2024)"},{"key":"23_CR26","unstructured":"Perron, L., Didier, F., Gay, S.: The CP-SAT-LP solver. In: the International Conference on Principles and Practice of Constraint Programming, vol.\u00a0280, pp. 3:1\u20133:2 (2023)"},{"key":"23_CR27","unstructured":"Pirnay, J., Grimm, D.G.: Self-improvement for neural combinatorial optimization: Sample without replacement, but improvement. Trans. Mach. Learn. Res. (2024). https:\/\/openreview.net\/forum?id=agT8ojoH0X"},{"key":"23_CR28","unstructured":"Qiu, W., Zhu, H.: Programmatic reinforcement learning without oracles. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=6Tk2noBdvxt"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Reijnen, R., Smit, I.G., Zhang, H., Wu, Y., Bukhsh, Z., Zhang, Y.: Job shop scheduling benchmark: Environments and instances for learning and non-learning methods. Ann. Math. Artif. Intell. 1\u201331 (2026)","DOI":"10.1007\/s10472-026-10007-3"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Remmerden, J.V., Bukhsh, Z., Zhang, Y.: Offline reinforcement learning for learning to dispatch for job shop scheduling. Mach. Learn. 114(8), 191 (2025)","DOI":"10.1007\/s10994-025-06826-w"},{"key":"23_CR31","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"15","key":"23_CR32","doi-asserted-by":"publisher","first-page":"4255","DOI":"10.1080\/00207543.2011.611539","volume":"50","author":"V Sels","year":"2012","unstructured":"Sels, V., Gheysen, N., Vanhoucke, M.: A comparison of priority rules for the job shop scheduling problem under different flow time-and tardiness-related objective functions. Int. J. Prod. Res. 50(15), 4255\u20134270 (2012)","journal-title":"Int. J. Prod. Res."},{"issue":"1","key":"23_CR33","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","volume":"104","author":"B Shahriari","year":"2016","unstructured":"Shahriari, B., Swersky, K., Wang, Z., Adams, R.P., De Freitas, N.: Taking the human out of the loop: a review of Bayesian optimization. Proc. IEEE 104(1), 148\u2013175 (2016)","journal-title":"Proc. IEEE"},{"issue":"10","key":"23_CR34","doi-asserted-by":"publisher","first-page":"1495","DOI":"10.1287\/mnsc.38.10.1495","volume":"38","author":"RH Storer","year":"1992","unstructured":"Storer, R.H., Wu, S.D., Vaccari, R.: New search spaces for sequencing problems with application to job shop scheduling. Manage. Sci. 38(10), 1495\u20131509 (1992)","journal-title":"Manage. Sci."},{"key":"23_CR35","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (2018)"},{"issue":"2","key":"23_CR36","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/0377-2217(93)90182-M","volume":"64","author":"E Taillard","year":"1993","unstructured":"Taillard, E.: Benchmarks for basic scheduling problems. Eur. J. Oper. Res. 64(2), 278\u2013285 (1993)","journal-title":"Eur. J. Oper. Res."},{"key":"23_CR37","first-page":"25146","volume":"34","author":"D Trivedi","year":"2021","unstructured":"Trivedi, D., Zhang, J., Sun, S.H., Lim, J.J.: Learning to synthesize programs as interpretable and generalizable policies. Adv. Neural. Inf. Process. Syst. 34, 25146\u201325163 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR38","doi-asserted-by":"publisher","first-page":"74952","DOI":"10.52202\/075280-3275","volume":"36","author":"M Turpin","year":"2023","unstructured":"Turpin, M., Michael, J., Perez, E., Bowman, S.: Language models don\u2019t always say what they think: unfaithful explanations in chain-of-thought prompting. Adv. Neural. Inf. Process. Syst. 36, 74952\u201374965 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR39","doi-asserted-by":"publisher","first-page":"101649","DOI":"10.1016\/j.jocs.2022.101649","volume":"61","author":"M \u0110urasevi\u0107","year":"2022","unstructured":"\u0110urasevi\u0107, M., Jakobovi\u0107, D.: Selection of dispatching rules evolved by genetic programming in dynamic unrelated machines scheduling based on problem characteristics. J. Comput. Sci. 61, 101649 (2022)","journal-title":"J. Comput. Sci."},{"key":"23_CR40","unstructured":"Verma, A., Le, H.M., Yue, Y., Chaudhuri, S.: Imitation-projected programmatic reinforcement learning. In: the 33rd International Conference on Neural Information Processing Systems, pp. 15752\u201315763 (2019)"},{"key":"23_CR41","unstructured":"Verma, A., Murali, V., Singh, R., Kohli, P., Chaudhuri, S.: Programmatically interpretable reinforcement learning. In: International Conference on Machine Learning, pp. 5045\u20135054. PMLR (2018)"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Minimizing latency for multi-DNN inference on resource-limited CPU-only edge devices. In: the IEEE Conference on Computer Communications, pp. 2239\u20132248. IEEE (2024)","DOI":"10.1109\/INFOCOM52122.2024.10621120"},{"key":"23_CR43","doi-asserted-by":"publisher","first-page":"107790","DOI":"10.1016\/j.engappai.2023.107790","volume":"131","author":"X Wu","year":"2024","unstructured":"Wu, X., Yan, X., Guan, D., Wei, M.: A deep reinforcement learning model for dynamic job-shop scheduling problem with uncertain processing time. Eng. Appl. Artif. Intell. 131, 107790 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"23_CR44","unstructured":"Yamada, T., Nakano, R.: A genetic algorithm applicable to large-scale job-shop problems. Parallel Probl. Solving Nat. 2, 281\u2013290 (1992)"},{"issue":"2","key":"23_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3701236","volume":"5","author":"WB Yates","year":"2025","unstructured":"Yates, W.B., Keedwell, E.C., Kheiri, A.: Explainable optimisation through online and offline hyper-heuristics. ACM Trans. Evol. Learn. 5(2), 1\u201329 (2025)","journal-title":"ACM Trans. Evol. Learn."},{"key":"23_CR46","unstructured":"Zhang, C., Cao, Z., Song, W., Wu, Y., Zhang, J.: Deep reinforcement learning guided improvement heuristic for job shop scheduling. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"23_CR47","first-page":"1621","volume":"33","author":"C Zhang","year":"2020","unstructured":"Zhang, C., Song, W., Cao, Z., Zhang, J., Tan, P.S., Chi, X.: Learning to dispatch for job shop scheduling via deep reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 1621\u20131632 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37670-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:43:26Z","timestamp":1788727406000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37670-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"ISBN":["9783032376695","9783032376701"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37670-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]},"assertion":[{"value":"7 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors used Opus 4.8 for proofreading. The authors reviewed these edits, and take full responsibility for the content of the paper including all scientific claims and results.","order":1,"name":"Ethics","label":"Generative AI Declaration","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Naples","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}