{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T04:04:55Z","timestamp":1780373095807,"version":"3.54.1"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032272416","type":"print"},{"value":"9783032272423","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-27242-3_2","type":"book-chapter","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T03:24:38Z","timestamp":1780370678000},"page":"19-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["corl: Reinforcement Learning of\u00a0MILP Policies Solved via\u00a0Branch-and-Bound"],"prefix":"10.1007","author":[{"given":"Akhil S.","family":"Anand","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elias","family":"Aarekol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin Mziray","family":"Dalseg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Magnus","family":"St\u00e5lhane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastien","family":"Gros","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"2_CR1","unstructured":"Amos, B., Yarats, D.: The differentiable cross-entropy method. In: Proceedings of the 37th International Conference on Machine Learning, pp. 291\u2013302. PMLR (2020)"},{"key":"2_CR2","unstructured":"Anand, A.S., Kordabad, A.B., Zanon, M., Gros, S.: Optimality conditions for model predictive control: Rethinking predictive model design. arXiv:2412.18268 (2024)"},{"key":"2_CR3","unstructured":"Anand, A.S., Sawant, S., Hoffmann, J., Reinhardt, D., Gros, S.: Closing the sim2real performance gap in rl. arXiv:2510.17709 (2025)"},{"issue":"15","key":"2_CR4","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.ifacol.2024.08.507","volume":"58","author":"AS Anand","year":"2024","unstructured":"Anand, A.S., Sawant, S., Reinhardt, D., Gros, S.: Data-driven predictive control and mpc: Do we achieve optimality? IFAC-Papers OnLine 58(15), 73\u201378 (2024)","journal-title":"IFAC-Papers OnLine"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Anand, A.S., Sawant, S., Reinhardt, D.P., Gros, S.: Predicting what matters: Training ai models for better decisions. IEEE Trans. Neural Netw. Learn. Syst. (2025)","DOI":"10.1109\/TNNLS.2025.3633573"},{"key":"2_CR6","unstructured":"Bellman, R.: Dynamic Programming Princeton University Press Princeton, pp. 24\u201373. New Jersey Google Scholar (1957)"},{"key":"2_CR7","unstructured":"Bello, I., Pham, H., Le, Q.V., Norouzi, M., Bengio, S.: Neural combinatorial optimization with reinforcement learning, arXiv:1611.09940 (2016)"},{"key":"2_CR8","first-page":"9508","volume":"33","author":"Q Berthet","year":"2020","unstructured":"Berthet, Q., Blondel, M., Teboul, O., Cuturi, M., Vert, J.P., Bach, F.: Learning with differentiable perturbed optimizers. Adv. Neural. Inf. Process. Syst. 33, 9508\u20139519 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Eiselt, H.A., Sandblom, C.L.: Operations research: A model-based approach, Springer Nature (2022)","DOI":"10.1007\/978-3-030-97162-5"},{"issue":"1","key":"2_CR10","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1287\/mnsc.2020.3922","volume":"68","author":"AN Elmachtoub","year":"2022","unstructured":"Elmachtoub, A.N., Grigas, P.: Smart \u201cpredict, then optimize\u2019\u2019. Manag. Sci. 68(1), 9\u201326 (2022)","journal-title":"Manag. Sci."},{"key":"2_CR11","unstructured":"Farahmand, A., Barreto, A., Nikovski, D.: Value-aware loss function for model-based reinforcement learning. In: Artificial Intelligence and Statistics. pp. 1486\u20131494. PMLR (2017)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Ferber, A., Wilder, B., Dilkina, B., Tambe, M.: Mipaal: Mixed integer program as a layer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 1504\u20131511 (2020)","DOI":"10.1609\/aaai.v34i02.5509"},{"key":"2_CR13","first-page":"7773","volume":"34","author":"C Grimm","year":"2021","unstructured":"Grimm, C., Barreto, A., Farquhar, G., Silver, D., Singh, S.: Proper value equivalence. Adv. Neural. Inf. Process. Syst. 34, 7773\u20137786 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"2_CR14","doi-asserted-by":"publisher","first-page":"5219","DOI":"10.1016\/j.ifacol.2020.12.1196","volume":"53","author":"S Gros","year":"2020","unstructured":"Gros, S., Zanon, M.: Reinforcement learning for mixed-integer problems based on mpc. IFAC-PapersOnLine 53(2), 5219\u20135224 (2020)","journal-title":"IFAC-PapersOnLine"},{"key":"2_CR15","unstructured":"Gurobi Optimization, LLC: Gurobi Optimizer Reference Manual (2024). https:\/\/www.gurobi.com"},{"key":"2_CR16","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Khalil, E., Le Bodic, P., Song, L., Nemhauser, G., Dilkina, B.: Learning to branch in mixed integer programming. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.10080"},{"key":"2_CR18","unstructured":"Korte, B., Vygen, J.: Combinatorial optimization: theory and algorithms, Springer (2008)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Kotary, J., Fioretto, F., Van Hentenryck, P., Wilder, B.: End-to-end constrained optimization learning: A survey, arXiv:2103.16378 (2021)","DOI":"10.24963\/ijcai.2021\/610"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Kuhn, H.W., Tucker, A.W.: Nonlinear programming. In: Traces and emergence of nonlinear programming, pp. 247\u2013258. Springer, Cham (2013)","DOI":"10.1007\/978-3-0348-0439-4_11"},{"key":"2_CR21","unstructured":"Lee, T.H., Kim, M.S.: Rl-milp solver: A reinforcement learning approach for solving mixed-integer linear programs with graph neural networks, arXiv:2411.19517 (2024)"},{"key":"2_CR22","unstructured":"Ma, Q., Ge, S., He, D., Thaker, D., Drori, I.: Combinatorial optimization by graph pointer networks and hierarchical reinforcement learning, arXiv:1911.04936 (2019)"},{"key":"2_CR23","unstructured":"Mandi, J., Bucarey, V., Tchomba, M.M.K., Guns, T.: Decision-focused learning: Through the lens of learning to rank. In: International Conference on Machine Learning, pp. 14935\u201314947. PMLR (2022)"},{"key":"2_CR24","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1613\/jair.1.15320","volume":"80","author":"J Mandi","year":"2024","unstructured":"Mandi, J., et al.: Decision-focused learning: Foundations, state of the art, benchmark and future opportunities. J. Artif. Intell. Res. 80, 1623\u20131701 (2024)","journal-title":"J. Artif. Intell. Res."},{"key":"2_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105400","volume":"134","author":"N Mazyavkina","year":"2021","unstructured":"Mazyavkina, N., Sviridov, S., Ivanov, S., Burnaev, E.: Reinforcement learning for combinatorial optimization: a survey. Comput. Oper. Res. 134, 105400 (2021)","journal-title":"Comput. Oper. Res."},{"issue":"2","key":"2_CR26","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1111\/1468-0262.00296","volume":"70","author":"P Milgrom","year":"2002","unstructured":"Milgrom, P., Segal, I.: Envelope theorems for arbitrary choice sets. Econometrica 70(2), 583\u2013601 (2002)","journal-title":"Econometrica"},{"issue":"3","key":"2_CR27","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1080\/01605682.2023.2253852","volume":"75","author":"F Petropoulos","year":"2024","unstructured":"Petropoulos, F., Laporte, G., Aktas, E., Alumur, S.A., Archetti, C., Ayhan, H., Battarra, M., Bennell, J.A., Bourjolly, J.M., Boylan, J.E., et al.: Operational research: methods and applications. J. Oper. Res. Soc. 75(3), 423\u2013617 (2024)","journal-title":"J. Oper. Res. Soc."},{"key":"2_CR28","unstructured":"Pogan\u010di\u0107, M.V., Paulus, A., Musil, V., Martius, G., Rolinek, M.: Differentiation of blackbox combinatorial solvers. In: International Conference on Learning Representations (2019)"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Powell, W.B.: Clearing the jungle of stochastic optimization. In: Bridging Data and Decisions, pp. 109\u2013137. Informs (2014)","DOI":"10.1287\/educ.2014.0128"},{"key":"2_CR30","unstructured":"Puterman, M.L.: Markov decision processes: discrete stochastic dynamic programming. John Wiley & Sons (2014)"},{"key":"2_CR31","unstructured":"Qi, M., Wang, M., Shen, Z.J.: Smart feasibility pump: Reinforcement learning for (mixed) integer programming, arXiv preprint arXiv:2102.09663 (2021)"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Reiter, R., et al.: Synthesis of model predictive control and reinforcement learning: Survey and classification. arXiv preprint arXiv:2502.02133 (2025)","DOI":"10.1016\/j.arcontrol.2026.101045"},{"key":"2_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0927-0507(03)10001-1","volume":"10","author":"A Ruszczy\u0144ski","year":"2003","unstructured":"Ruszczy\u0144ski, A., Shapiro, A.: Stochastic programming models. Handbooks Oper. Res. Manag. Sci. 10, 1\u201364 (2003)","journal-title":"Handbooks Oper. Res. Manag. Sci."},{"issue":"2","key":"2_CR34","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.ejor.2024.03.020","volume":"320","author":"U Sadana","year":"2025","unstructured":"Sadana, U., Chenreddy, A., Delage, E., Forel, A., Frejinger, E., Vidal, T.: A survey of contextual optimization methods for decision-making under uncertainty. Eur. J. Oper. Res. 320(2), 271\u2013289 (2025)","journal-title":"Eur. J. Oper. Res."},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Scavuzzo, L., Aardal, K., Lodi, A., Yorke-Smith, N.: Machine learning augmented branch and bound for mixed integer linear programming. Math. Program. 1\u201344 (2024)","DOI":"10.1007\/s10107-024-02130-y"},{"issue":"7839","key":"2_CR36","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","journal-title":"Nature"},{"key":"2_CR37","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms, arXiv preprint arXiv:1707.06347 (2017)"},{"key":"2_CR38","unstructured":"Wei, R., Lambert, N., McDonald, A.D., Garcia, A., Calandra, R.: A unified view on solving objective mismatch in model-based reinforcement learning. Trans. Mach. Learn. Res. (2024), survey Certification"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Wilder, B., Dilkina, B., Tambe, M.: Melding the data-decisions pipeline: decision-focused learning for combinatorial optimization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 1658\u20131665 (2019)","DOI":"10.1609\/aaai.v33i01.33011658"},{"key":"2_CR40","unstructured":"Wolsey, L.A., Nemhauser, G.L.: Integer and combinatorial optimization. John Wiley & Sons (1999)"},{"key":"2_CR41","unstructured":"Xu, L., Wilder, B., Khalil, E.B., Tambe, M.: Reinforcement learning with combinatorial actions for coupled restless bandits, arXiv preprint arXiv:2503.01919 (2025)"},{"key":"2_CR42","unstructured":"Yahoo Finance: Yahoo finance (nd). https:\/\/finance.yahoo.com\/. Accessed 17 Mar 2026"}],"container-title":["Lecture Notes in Computer Science","Integration of Constraint Programming, Artificial Intelligence, and Operations Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-27242-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T03:24:46Z","timestamp":1780370686000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-27242-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032272416","9783032272423"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-27242-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CPAIOR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rabat","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","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":"26 May 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cpaior2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/cpaior2026\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}