{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T09:08:47Z","timestamp":1784538527614,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3788550.3794866","type":"proceedings-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:46:11Z","timestamp":1784537171000},"page":"38-42","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust Exploration in Directed Controller Synthesis via Mixture-of-Experts Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1033-3383","authenticated-orcid":false,"given":"Toshihide","family":"Ubukata","sequence":"first","affiliation":[{"name":"Waseda University, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3003-8902","authenticated-orcid":false,"given":"Mingyue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Southwest University, Chongqing, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7282-5652","authenticated-orcid":false,"given":"Zhiyao","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Osaka, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8960-7770","authenticated-orcid":false,"given":"Nianyu","family":"Li","sequence":"additional","affiliation":[{"name":"ZGC Lab, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4327-1807","authenticated-orcid":false,"given":"Jialong","family":"Li","sequence":"additional","affiliation":[{"name":"Waseda University, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1106-1709","authenticated-orcid":false,"given":"Kenji","family":"Tei","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","first-page":"4892","DOI":"10.23919\/ACC50511.2021.9482704","volume-title":"2021 American Control Conference (ACC)","author":"Alrahman Yehia\u00a0Abd","year":"2021","unstructured":"Yehia\u00a0Abd Alrahman, Victor Braberman, Nicol\u00e1s D\u2019Ippolito, Nir Piterman, and Sebastian Uchitel. 2021. Synthesis of Run-To-Completion Controllers for Discrete Event Systems. In 2021 American Control Conference (ACC). 4892\u20134899. 10.23919\/ACC50511.2021.9482704"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEAMS59076.2023.00012"},{"key":"e_1_3_3_2_4_2","first-page":"2","volume-title":"Proceedings of the 19th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS)","author":"Carwehl Marc","year":"2024","unstructured":"Marc Carwehl, Calum Imrie, Thomas Vogel, Gena\u00edna Rodrigues, Radu Calinescu, and Lars Grunske. 2024. Formal Synthesis of Uncertainty Reduction Controllers. In Proceedings of the 19th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS). 2\u201313. 10.1145\/3643915.3644095"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-68612-7"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.1109\/CDC40024.2019.9029766","volume-title":"2019 IEEE 58th Conference on Decision and Control (CDC)","author":"Castellano Ezequiel","year":"2019","unstructured":"Ezequiel Castellano, Victor Braberman, Nicol\u00e1s D\u2019Ippolito, Sebasti\u00e1n Uchitel, and Kenji Tei. 2019. Minimising Makespan of Discrete Controllers: A Qualitative Approach. In 2019 IEEE 58th Conference on Decision and Control (CDC) (Nice, France). IEEE Press, 1068\u20131075. 10.1109\/CDC40024.2019.9029766"},{"key":"e_1_3_3_2_7_2","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Chow Yinlam","year":"2023","unstructured":"Yinlam Chow, Aza Tulepbergenov, Ofir Nachum, Dhawal Gupta, Moonkyung Ryu, Mohammad Ghavamzadeh, and Craig Boutilier. 2023. A Mixture-of-Expert Approach to RL-based Dialogue Management. In The Eleventh International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_8_2","series-title":"(CDC)","first-page":"4764","volume-title":"Proc. of the IEEE Conf. on Decision and Control","author":"Ciolek D.","year":"2016","unstructured":"D. Ciolek, V. Braberman, N. D\u2019Ippolito, and S. Uchitel. 2016. Directed Controller Synthesis of discrete event systems: Taming composition with heuristics. In Proc. of the IEEE Conf. on Decision and Control(CDC). 4764\u20134769."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Daniel Ciolek Matias Duran Florencia Zanollo Nicolas Pazos Juli\u00e1n Braier Victor Braberman Nicolas D\u2019Ippolito and Sebastian Uchitel. 2023. On-the-fly informed search of non-blocking directed controllers. Automatica 147 (2023) 110731.","DOI":"10.1016\/j.automatica.2022.110731"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Daniel\u00a0Alfredo Ciolek Victor Braberman Nicol\u00e1s D\u2019Ippolito Sebasti\u00e1n Sardi\u00f1a and Sebasti\u00e1n Uchitel. 2020. Compositional Supervisory Control via Reactive Synthesis and Automated Planning. IEEE Trans. Automat. Control 65 8 (2020) 3502\u20133516. 10.1109\/TAC.2019.2948270","DOI":"10.1109\/TAC.2019.2948270"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Daniel\u00a0Alfredo Ciolek Victor Braberman Nicol\u00e1s D\u2019Ippolito Sebasti\u00e1n Sardi\u00f1a and Sebasti\u00e1n Uchitel. 2020. Compositional Supervisory Control via Reactive Synthesis and Automated Planning. IEEE Trans. Automat. Control 65 8 (2020) 3502\u20133516. 10.1109\/TAC.2019.2948270","DOI":"10.1109\/TAC.2019.2948270"},{"key":"e_1_3_3_2_12_2","series-title":"Proceedings of the 36th International Conference on Machine Learning","first-page":"1282","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Cobbe Karl","year":"2019","unstructured":"Karl Cobbe, Oleg Klimov, Chris Hesse, Taehoon Kim, and John Schulman. 2019. Quantifying Generalization in Reinforcement Learning. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of the 36th International Conference on Machine Learning, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). 1282\u20131289."},{"key":"e_1_3_3_2_13_2","first-page":"569","volume-title":"Proceedings of the 33rd International Conference on Automated Planning and Scheduling (ICAPS)","author":"Delgado Tom\u00e1s","year":"2023","unstructured":"Tom\u00e1s Delgado, Marco\u00a0S\u00e1nchez Sorondo, V\u00edctor Braberman, and Sebasti\u00e1n Uchitel. 2023. Exploration Policies for On-the-Fly Controller Synthesis: A Reinforcement Learning Approach. In Proceedings of the 33rd International Conference on Automated Planning and Scheduling (ICAPS). AAAI Press, 569\u2013577."},{"key":"e_1_3_3_2_14_2","first-page":"475","volume-title":"23rd IEEE\/ACM International Conference on Automated Software Engineering (ASE)","author":"D\u2019Ippolito Nicolas","year":"2008","unstructured":"Nicolas D\u2019Ippolito, Dario Fischbein, Marsha Chechik, and Sebastian Uchitel. 2008. MTSA: The Modal Transition System Analyser. In 23rd IEEE\/ACM International Conference on Automated Software Engineering (ASE). 475\u2013476. 10.1109\/ASE.2008.78"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/978-3-031-98685-7_10","volume-title":"Computer Aided Verification","author":"Gagliardi Hernan","year":"2025","unstructured":"Hernan Gagliardi, Victor Braberman, and Sebastian Uchitel. 2025. Scaling GR(1) Synthesis via a Compositional Framework for LTL Discrete Event Control. In Computer Aided Verification, Ruzica Piskac and Zvonimir Rakamari\u0107 (Eds.). Springer Nature Switzerland, Cham, 201\u2013223."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Dimitra Giannakopoulou and Jeff Magee. 2003. Fluent Model Checking for Event-Based Systems. SIGSOFT Softw. Eng. Notes 28 5 (Sept. 2003) 257\u2013266.","DOI":"10.1145\/949952.940106"},{"key":"e_1_3_3_2_17_2","volume-title":"The Twelfth International Conference on Learning Representations (ICLR)","author":"Hendawy Ahmed","year":"2024","unstructured":"Ahmed Hendawy, Jan Peters, and Carlo D\u2019Eramo. 2024. Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts. In The Twelfth International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_18_2","unstructured":"Suning Huang Zheyu Zhang Tianhai Liang Yihan Xu Zhehao Kou Chenhao Lu Guowei Xu Zhengrong Xue and Huazhe Xu. 2025. MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2410.14972\u00a0[cs.RO] https:\/\/arxiv.org\/abs\/2410.14972"},{"key":"e_1_3_3_2_19_2","first-page":"1","volume-title":"2024 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)","author":"Ishimizu Yusei","year":"2024","unstructured":"Yusei Ishimizu, Jialong Li, Takuto Yamauchi, Sinan Chen, Jinyu Cai, Takanori Hirano, and Kenji Tei. 2024. Towards Efficient Discrete Controller Synthesis: Semantics-Aware Stepwise Policy Design via LLM. In 2024 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia). 1\u20134. 10.1109\/ICCE-Asia63397.2024.10773792"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Robert\u00a0A. Jacobs Michael\u00a0I. Jordan Steven\u00a0J. Nowlan and Geoffrey\u00a0E. Hinton. 1991. Adaptive Mixtures of Local Experts. Neural Computation 3 1 (1991) 79\u201387. 10.1162\/neco.1991.3.1.79","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Maureen Keegan Victor Braberman Nicol\u00e1s D\u2019Ippolito Nir Piterman and Sebasti\u00e1n Uchitel. 2022. Control and Discovery of Environment Behaviour. IEEE Transactions on Software Engineering 48 6 (2022) 1965\u20131978. 10.1109\/TSE.2020.3044532","DOI":"10.1109\/TSE.2020.3044532"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"J.O. Kephart and D.M. Chess. 2003. The vision of autonomic computing. Computer 36 1 (2003) 41\u201350. 10.1109\/MC.2003.1160055","DOI":"10.1109\/MC.2003.1160055"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Robert Kirk Amy Zhang Edward Grefenstette and Tim Rockt\u00e4schel. 2023. A Survey of Zero-shot Generalisation in Deep Reinforcement Learning. Journal of Artificial Intelligence Research 76 (Jan. 2023) 201\u2013264. 10.1613\/jair.1.14174","DOI":"10.1613\/jair.1.14174"},{"key":"e_1_3_3_2_24_2","first-page":"33","volume-title":"2020 IEEE 18th International Conference on Embedded and Ubiquitous Computing (EUC)","author":"Li Jialong","year":"2020","unstructured":"Jialong Li, Kazuya Aizawa, Kenji Tei, and Shinichi Honiden. 2020. Efficient Difference Analysis Algorithm for Runtime Requirement Degradation under System Functional Fault. In 2020 IEEE 18th International Conference on Embedded and Ubiquitous Computing (EUC). 33\u201340."},{"key":"e_1_3_3_2_25_2","first-page":"1","volume-title":"Proceedings of the 12th ACM\/IEEE International Workshop on Software Engineering for Systems-of-Systems and Software Ecosystems (SESoS)","author":"Li Jialong","year":"2024","unstructured":"Jialong Li, Wallace Manzano, Takuto Yamauchi, Nobuhiro Matsuyama, Elisa\u00a0Yumi Nakagawa, and Kenji Tei. 2024. Employing Discrete Controller Synthesis for Developing Systems-of-Systems Controllers. In Proceedings of the 12th ACM\/IEEE International Workshop on Software Engineering for Systems-of-Systems and Software Ecosystems (SESoS) (Lisbon, Portugal). 1\u20138. 10.1145\/3643655.3643875"},{"key":"e_1_3_3_2_26_2","first-page":"288","volume-title":"2022 IEEE 30th International Requirements Engineering Conference (RE)","author":"Li Jialong","year":"2022","unstructured":"Jialong Li and Kenji Tei. 2022. Done is better than perfect: Iterative Adaptation via Multi-grained Requirement Relaxation. In 2022 IEEE 30th International Requirements Engineering Conference (RE). 288\u2013294. 10.1109\/RE54965.2022.00043"},{"key":"e_1_3_3_2_27_2","first-page":"96","volume-title":"Proceedings of the 11th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS)","author":"Nahabedian L.","year":"2016","unstructured":"L. Nahabedian, V. Braberman, N. D\u2019Ippolito, S. Honiden, J. Kramer, K. Tei, and S. Uchitel. 2016. Assured and correct dynamic update of controllers. In Proceedings of the 11th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS). 96\u2013107. 10.1145\/2897053.2897056"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"Leandro Nahabedian Victor Braberman Nicol\u00e1s D\u2019Ippolito Shinichi Honiden Jeff Kramer Kenji Tei and Sebasti\u00e1n Uchitel. 2020. Dynamic Update of Discrete Event Controllers. IEEE Trans. Softw. Eng. 46 11 (Nov. 2020) 1220\u20131240. 10.1109\/TSE.2018.2876843","DOI":"10.1109\/TSE.2018.2876843"},{"key":"e_1_3_3_2_29_2","volume-title":"Proceedings of the 41st International Conference on Machine Learning (ICML)","author":"Obando-Ceron Johan","year":"2024","unstructured":"Johan Obando-Ceron, Ghada Sokar, Timon Willi, Clare Lyle, Jesse Farebrother, Jakob Foerster, Karolina Dziugaite, Doina Precup, and Pablo\u00a0Samuel Castro. 2024. Mixtures of experts unlock parameter scaling for deep RL. In Proceedings of the 41st International Conference on Machine Learning (ICML) (Vienna, Austria). Article 1563, 21\u00a0pages."},{"key":"e_1_3_3_2_30_2","unstructured":"Noam Shazeer Azalia Mirhoseini Krzysztof Maziarz Andy Davis Quoc Le Geoffrey Hinton and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. arxiv:https:\/\/arXiv.org\/abs\/1701.06538\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1701.06538"},{"key":"e_1_3_3_2_31_2","volume-title":"Reinforcement Learning: An Introduction (2nd ed.)","author":"Sutton Richard\u00a0S.","year":"2018","unstructured":"Richard\u00a0S. Sutton and Andrew\u00a0G. Barto. 2018. Reinforcement Learning: An Introduction (2nd ed.). MIT Press, Cambridge, MA."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48119-2_15"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1109\/QRS-C65679.2025.00104","volume-title":"2025 25th International Conference on Software Quality, Reliability, and Security Companion (QRS-C)","author":"Ubukata Toshihide","year":"2025","unstructured":"Toshihide Ubukata, Mingyue Zhang, Takuto Yamauchi, Jialong Li, and Kenji Tei. 2025. Graph-Contextual Reinforcement Learning for Efficient Exploration in Directed Controller Synthesis. In 2025 25th International Conference on Software Quality, Reliability, and Security Companion (QRS-C). 777\u2013779. 10.1109\/QRS-C65679.2025.00104"},{"key":"e_1_3_3_2_34_2","first-page":"1","volume-title":"Proceedings of the 11th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS)","author":"Uchitel Sebastian","year":"2016","unstructured":"Sebastian Uchitel, Victor\u00a0A. Braberman, and Nicolas D\u2019Ippolito. 2016. Runtime controller synthesis for self-adaptation: be discrete!. In Proceedings of the 11th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS) (Austin, Texas). 1\u20133. 10.1145\/2897053.2903381"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Marko Vasi\u0107 Andrija Petrovi\u0107 Kaiyuan Wang Mladen Nikoli\u0107 Rishabh Singh and Sarfraz Khurshid. 2022. Mo\u00cbT: Mixture of Expert Trees and its application to verifiable reinforcement learning. Neural Networks 151 (2022) 34\u201347. 10.1016\/j.neunet.2022.03.022","DOI":"10.1016\/j.neunet.2022.03.022"},{"key":"e_1_3_3_2_36_2","volume-title":"Advances in Neural Information Processing Systems (2022NeurIPS)","author":"Wang Qi","year":"2022","unstructured":"Qi Wang and Herke van Hoof. 2022. Learning Expressive Meta-Representations with Mixture of Expert Neural Processes. In Advances in Neural Information Processing Systems (2022NeurIPS), Alice\u00a0H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (Eds.)."},{"key":"e_1_3_3_2_37_2","unstructured":"Timon Willi Johan Obando-Ceron Jakob Foerster Karolina Dziugaite and Pablo\u00a0Samuel Castro. 2024. Mixture of Experts in a Mixture of RL settings. arxiv:https:\/\/arXiv.org\/abs\/2406.18420\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2406.18420"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1109\/CDC.1984.272178","volume-title":"The 23rd IEEE Conference on Decision and Control","author":"Wonham W.\u00a0M.","year":"1984","unstructured":"W.\u00a0M. Wonham and P.\u00a0J. Ramadge. 1984. On the supremal controllable sublanguage of a given language. In The 23rd IEEE Conference on Decision and Control. 1073\u20131080. 10.1109\/CDC.1984.272178"},{"key":"e_1_3_3_2_39_2","unstructured":"Wenhao Wu Fuhong Liu Haoru Li Zican Hu Daoyi Dong Chunlin Chen and Zhi Wang. 2025. Mixture-of-Experts Meets In-Context Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2506.05426\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2506.05426"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Takuto Yamauchi and Kenji Tei. 2023. An Analysis Space Reduction for Discrete Controller Synthesis by Stepwise Partial Synthesis. IEICE Transactions D J106-D 4 (April 2023) 218\u2013230. 10.14923\/transinfj.2022PDP0022","DOI":"10.14923\/transinfj.2022PDP0022"}],"event":{"name":"SEAMS '26: 21st International Conference on Software Engineering for Adaptive and Self-Managing Systems","location":"Rio de Janeiro Brazil","acronym":"SEAMS '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS"]},"container-title":["Proceedings of the 21st International Conference on Software Engineering for Adaptive and Self-Managing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788550.3794866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:51:09Z","timestamp":1784537469000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788550.3794866"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":39,"alternative-id":["10.1145\/3788550.3794866","10.1145\/3788550"],"URL":"https:\/\/doi.org\/10.1145\/3788550.3794866","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}