{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T04:07:07Z","timestamp":1780373227066,"version":"3.54.1"},"publisher-location":"Cham","reference-count":55,"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_6","type":"book-chapter","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T03:25:12Z","timestamp":1780370712000},"page":"82-100","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Imitation-Guided World Models for\u00a0Multi-agent Train Rescheduling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1717-0522","authenticated-orcid":false,"given":"Max","family":"Bourgeat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2903-9593","authenticated-orcid":false,"given":"Antoine","family":"Legrain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8742-0774","authenticated-orcid":false,"given":"Quentin","family":"Cappart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"6_CR1","unstructured":"Barcellona, L., Zadaianchuk, A., Allegro, D., Papa, S., Ghidoni, S., Gavves, E.: Dream to manipulate: Compositional world models empowering robot imitation learning with imagination. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=3RSLW9YSgk"},{"issue":"3731","key":"6_CR2","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1126\/science.153.3731.34","volume":"153","author":"R Bellman","year":"1966","unstructured":"Bellman, R.: Dynamic programming. Science 153(3731), 34\u201337 (1966)","journal-title":"Science"},{"key":"6_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-319-59776-8_26","volume-title":"Integration of AI and OR Techniques in Constraint Programming","author":"Q Cappart","year":"2017","unstructured":"Cappart, Q., Schaus, P.: Rescheduling Railway Traffic on Real Time Situations Using Time-Interval Variables. In: Salvagnin, D., Lombardi, M. (eds.) CPAIOR 2017. LNCS, vol. 10335, pp. 312\u2013327. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-59776-8_26"},{"key":"6_CR4","unstructured":"Cobbe, K., Klimov, O., Hesse, C., Kim, T., Schulman, J.: Quantifying generalization in reinforcement learning. In: International Conference on Machine Learning, pp. 1282\u20131289. PMLR (2019)"},{"key":"6_CR5","unstructured":"DeMoss, B., Duckworth, P., Hawes, N., Posner, I.: Ditto: Offline imitation learning with world models. arXiv preprint arXiv:2302.03086 (2023)"},{"key":"6_CR6","unstructured":"Egorov, V., Shpilman, A.: Scalable multi-agent model-based reinforcement learning. In: Proceedings of the 21st International Conference on Autonomous Agents and MultiAgent Systems (AAMAS 2022), pp. 381\u2013389. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) (2022). https:\/\/arxiv.org\/abs\/2205.15023, online 9\u201313 May 2022"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018), pp. 2974\u20132982 (2018), https:\/\/arxiv.org\/abs\/1705.08926","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"6_CR8","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: Proceedings of the 36th International Conference on Machine Learning (ICML), pp. 2555\u20132565 (2019). https:\/\/arxiv.org\/abs\/1811.04551"},{"key":"6_CR9","unstructured":"Hafner, D., Lillicrap, T.P., Ba, J., Norouzi, M.: Dream to control: Learning behaviors by latent imagination. In: International Conference on Learning Representations (ICLR) (2020). https:\/\/arxiv.org\/abs\/1912.01603, spotlight"},{"key":"6_CR10","unstructured":"Hafner, D., Lillicrap, T.P., Norouzi, M., Ba, J.: Mastering atari with discrete world models. In: International Conference on Learning Representations (ICLR) (2021). https:\/\/openreview.net\/forum?id=5r6uxv1h5V, accepted as spotlight"},{"issue":"6","key":"6_CR11","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1007\/s10458-019-09421-1","volume":"33","author":"P Hernandez-Leal","year":"2019","unstructured":"Hernandez-Leal, P., Kartal, B., Taylor, M.E.: A survey and critique of multiagent deep reinforcement learning. Auton. Agent. Multi-Agent Syst. 33(6), 750\u2013797 (2019)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Ho, F., Goncalves, A., Salta, A., Cavazza, M., Geraldes, R., Prendinger, H.: Multi-agent path finding for UAV traffic management: Robotics track, pp. 131\u2013139 (2019)","DOI":"10.65109\/YIYZ4967"},{"key":"6_CR13","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. Adv. Neural. Inf. Process. Syst. 29 (2016)"},{"key":"6_CR14","unstructured":"Huh, D., Mohapatra, P.: Multi-agent reinforcement learning: A comprehensive survey, arXiv preprint arXiv:2312.10256 (2023)"},{"issue":"2","key":"6_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3054912","volume":"50","author":"A Hussein","year":"2017","unstructured":"Hussein, A., Gaber, M.M., Elyan, E., Jayne, C.: Imitation learning: a survey of learning methods. ACM Comput. Surv. (CSUR) 50(2), 1\u201335 (2017)","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"4","key":"6_CR16","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1109\/TRO.2018.2853613","volume":"34","author":"W H\u00f6nig","year":"2018","unstructured":"H\u00f6nig, W., Preiss, J.A., Kumar, T.K.S., Sukhatme, G.S., Ayanian, N.: Trajectory planning for quadrotor swarms. IEEE Trans. Rob. 34(4), 856\u2013869 (2018). https:\/\/doi.org\/10.1109\/TRO.2018.2853613","journal-title":"IEEE Trans. Rob."},{"key":"6_CR17","unstructured":"Jaziri, A., K\u00fcnzel, E., Ramesh, V.: Mitigating the stability-plasticity dilemma in adaptive train scheduling with curriculum-driven continual dqn expansion. CoRR abs\/2408.09838 (2024). https:\/\/doi.org\/10.48550\/arXiv.2408.09838"},{"key":"6_CR18","unstructured":"Kinga, D., Adam, J.B.: A method for stochastic optimization. In: International Conference on Learning Representations (ICLR), vol. 5, California (2015)"},{"issue":"4598","key":"6_CR19","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1126\/science.220.4598.671","volume":"220","author":"S Kirkpatrick","year":"1983","unstructured":"Kirkpatrick, S., Gelatt, C., Vecchi, M.: Optimization by simulated annealing. Science 220(4598), 671\u2013680 (1983). https:\/\/doi.org\/10.1126\/science.220.4598.671","journal-title":"Science"},{"key":"6_CR20","unstructured":"Konda, V., Tsitsiklis, J.: Actor-critic algorithms. Adv. Neural. Inf. Process. Syst. 12 (1999)"},{"key":"6_CR21","doi-asserted-by":"publisher","unstructured":"Li, J., et al.: Scalable rail planning and replanning: Winning the 2020 flatland challenge. Proc. Int. Conf. Autom. Plan. Sched. 31(1), 477\u2013485 (2021). https:\/\/doi.org\/10.1609\/icaps.v31i1.15994, https:\/\/ojs.aaai.org\/index.php\/ICAPS\/article\/view\/15994","DOI":"10.1609\/icaps.v31i1.15994"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Li, J., Tinka, A., Kiesel, S., Durham, J.W., Kumar, T.S., Koenig, S.: Lifelong multi-agent path finding in large-scale warehouses, pp. 11272\u201311281 (2021)","DOI":"10.1609\/aaai.v35i13.17344"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Liao, J., Zhang, F., Zhang, S., Gong, C.: A real-time train timetable rescheduling method based on deep learning for metro systems energy optimization under random disturbances. J. Adv. Transp. 2020(1), 8882554 (2020). https:\/\/doi.org\/10.1155\/2020\/8882554, https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1155\/2020\/8882554","DOI":"10.1155\/2020\/8882554"},{"key":"6_CR24","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning, arXiv preprint arXiv:1509.02971 (2015)"},{"issue":"3","key":"6_CR25","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MCI.2023.3277768","volume":"18","author":"S Liu","year":"2023","unstructured":"Liu, S., Zhang, Y., Tang, K., Yao, X.: How good is neural combinatorial optimization? a systematic evaluation on the traveling salesman problem. IEEE Comput. Intell. Mag. 18(3), 14\u201328 (2023)","journal-title":"IEEE Comput. Intell. Mag."},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Liu, X., da Silva, C.F.O., Dabiri, A., Wang, Y., De Schutter, B.: Learning-based model predictive control for passenger-oriented train rescheduling with flexible train composition. arXiv preprint arXiv:2502.15544 (2025)","DOI":"10.1016\/j.ifacol.2025.12.065"},{"key":"6_CR27","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Ma, H., Li, J., Kumar, T.S., Koenig, S.: Lifelong multi-agent path finding for online pickup and delivery tasks, pp. 837\u2013845 (2017)","DOI":"10.65109\/TNMO6004"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"6_CR30","unstructured":"Mohanty, S., et al.: Flatland-rl: Multi-agent reinforcement learning on trains (2020)"},{"key":"6_CR31","unstructured":"Oh, J., Guo, Y., Singh, S., Lee, H.: Self-imitation learning. In: Proceedings of the 35th International Conference on Machine Learning (ICML 2018), pp. 3878\u20133887. PMLR (2018). https:\/\/proceedings.mlr.press\/v80\/oh18b.html"},{"key":"6_CR32","unstructured":"Peng, X.B., Kumar, A., Zhang, G., Levine, S.: Advantage-weighted regression: Simple and scalable off-policy reinforcement learning, arXiv preprint arXiv:1910.00177 (2019)"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Phillips, M., Likhachev, M.: SIPP: Safe interval path planning for dynamic environments. In: 2011 IEEE International Conference on Robotics and Automation, pp. 5628\u20135635. IEEE (2011)","DOI":"10.1109\/ICRA.2011.5980306"},{"key":"6_CR34","unstructured":"Ross, S., Gordon, G., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 627\u2013635. JMLR Workshop and Conference Proceedings (2011)"},{"key":"6_CR35","unstructured":"Roy, J., Girgis, R., Romoff, J., Bacon, P.L., Pal, C.J.: Direct behavior specification via constrained reinforcement learning. In: International Conference on Machine Learning, pp. 18828\u201318843. PMLR (2022)"},{"key":"6_CR36","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017). https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Sharon, G., Stern, R., Felner, A., Sturtevant, N.: Conflict-based search for optimal multi-agent path finding. In: Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence. pp. 563\u2013569. AAAI\u201912, AAAI Press (2012)","DOI":"10.1609\/aaai.v26i1.8140"},{"key":"6_CR38","doi-asserted-by":"publisher","unstructured":"Shaw, P.: Using constraint programming and local search methods to solve vehicle routing problems. In: Proceedings of the 4th International Conference on Principles and Practice of Constraint Programming (CP\u201998), pp. 417\u2013431. Springer (1998). https:\/\/doi.org\/10.1007\/BFb0054171","DOI":"10.1007\/BFb0054171"},{"key":"6_CR39","unstructured":"Shi, Z., Liu, M., Zhang, S., Zheng, R., Dong, S., Wei, P.: Gawm: Global-aware world model for multi-agent reinforcement learning. arXiv preprint arXiv:2501.10116 (2025). https:\/\/arxiv.org\/abs\/2501.10116"},{"key":"6_CR40","unstructured":"Song, J., Ren, H., Sadigh, D., Ermon, S.: Multi-agent generative adversarial imitation learning. In: Advances in Neural Information Processing Systems, p. 31 (2018)"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Stern, R., et al.: Multi-agent pathfinding: Definitions, variants, and benchmarks. In: Proceedings of the International Symposium on Combinatorial Search, vol. 10, pp. 151\u2013158 (2019)","DOI":"10.1609\/socs.v10i1.18510"},{"key":"6_CR42","doi-asserted-by":"publisher","unstructured":"Surynek, P.: Problem compilation for multi-agent path finding: a survey. In: Raedt, L.D. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pp. 5615\u20135622. International Joint Conferences on Artificial Intelligence Organization (2022). https:\/\/doi.org\/10.24963\/ijcai.2022\/783, survey Track","DOI":"10.24963\/ijcai.2022\/783"},{"key":"6_CR43","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1, MIT press Cambridge (1998)"},{"key":"6_CR44","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. Adv. Neural Inf. Process. Syst. 12 (1999)"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Talvitie, E.: Self-correcting models for model-based reinforcement learning. In: Proceedings of the AAAI conference on artificial intelligence, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.10850"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Tang, J., Swamy, G., Fang, F., Wu, S.: Multi-agent imitation learning: Value is easy, regret is hard. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-0872"},{"key":"6_CR47","doi-asserted-by":"publisher","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 5998\u20136008 (2017). https:\/\/doi.org\/10.5555\/3295222.3295349, https:\/\/arxiv.org\/abs\/1706.03762","DOI":"10.5555\/3295222.3295349"},{"key":"6_CR48","doi-asserted-by":"crossref","unstructured":"Venugopal, A., Milani, S., Fang, F., Ravindran, B.: Mabl: Bi-level latent-variable world model for sample-efficient multi-agent reinforcement learning. In: Proceedings of the 23rd International Conference on Autonomous Agents and MultiAgent Systems (AAMAS 2024), pp. 1865\u20131873. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) (2024). https:\/\/www.ifaamas.org\/Proceedings\/aamas2024\/pdfs\/p1865.pdf","DOI":"10.65109\/WWBC9182"},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Wang, H., Yu, L., Cao, Z., Ermon, S.: Multi-agent Imitation Learning with Copulas. In: Oliver, N., P\u00b4 erez-Cruz, F., Kramer, S., Read, J., Lozano, J.A. (eds.) ECML PKDD 2021. LNCS (LNAI), vol. 12975, pp. 139\u2013156. Springer, Cham (2021).","DOI":"10.1007\/978-3-030-86486-6_9"},{"key":"6_CR50","doi-asserted-by":"crossref","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","DOI":"10.1007\/BF00992698"},{"issue":"3","key":"6_CR51","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1023\/A:1022672621406","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"6_CR52","doi-asserted-by":"crossref","unstructured":"Wu, Z., Yu, C., Chen, C., Hao, J., Zhuo, H.H.: Models as agents: optimizing multi-step predictions of interactive local models in model-based multi-agent reinforcement learning. In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI 2023). pp. 26241\u201326249. AAAI Press (2023). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/26241","DOI":"10.1609\/aaai.v37i9.26241"},{"key":"6_CR53","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Deekshith, U., Wang, J., Boedecker, J.: Improving the efficiency and efficacy of multi-agent reinforcement learning on complex railway networks with a local-critic approach. In: Proceedings of the International Conference on Automated Planning and Scheduling, Vol. 34, no. (1), pp. 698\u2013706 (2024). https:\/\/doi.org\/10.1609\/icaps.v34i1.31533, https:\/\/ojs.aaai.org\/index.php\/ICAPS\/article\/view\/31533","DOI":"10.1609\/icaps.v34i1.31533"},{"key":"6_CR54","unstructured":"Zheng, R., et al.: FLARE: Robot learning with implicit world modeling. In: Structured World Models for Robotic Manipulation (2025). https:\/\/openreview.net\/forum?id=rFiLBM4YCh"},{"key":"6_CR55","doi-asserted-by":"publisher","unstructured":"Zhu, Y., Wang, H., Goverde, R.M.: Reinforcement learning in railway timetable rescheduling. In: 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), pp. 1\u20136. IEEE Press (2020). https:\/\/doi.org\/10.1109\/ITSC45102.2020.9294188","DOI":"10.1109\/ITSC45102.2020.9294188"}],"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_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T03:25:29Z","timestamp":1780370729000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-27242-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032272416","9783032272423"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-27242-3_6","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"}}]}}