{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T04:11:29Z","timestamp":1687579889760},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T00:00:00Z","timestamp":1655942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T00:00:00Z","timestamp":1655942400000},"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":["Mach Learn"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s10994-021-06102-7","type":"journal-article","created":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T20:36:31Z","timestamp":1656016591000},"page":"3797-3838","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lifted model checking for relational MDPs"],"prefix":"10.1007","volume":"111","author":[{"given":"Wen-Chi","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Fran\u00e7ois","family":"Raskin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luc","family":"De Raedt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,6,23]]},"reference":[{"key":"6102_CR1","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., & Topcu, U. (2018). Safe reinforcement learning via shielding. In: Proceedings of the 32nd AAAI conference on artificial intelligence, (AAAI-18), the 30th innovative applications of artificial intelligence (IAAI-18), and the 8th AAAI symposium on educational advances in artificial intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2\u20137, 2018, (pp. 2669\u20132678)."},{"key":"6102_CR2","unstructured":"Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., & Man\u00e9, D. (2016). Concrete problems in AI safety. arXiv:1606.06565."},{"key":"6102_CR3","doi-asserted-by":"publisher","unstructured":"Bagheri Hariri, B., Calvanese, D., De Giacomo, G., Deutsch, A., & Montali, M. (2013). Verification of relational data-centric dynamic systems with external services (Vol. \u201913, pp. 163\u2013174). PODS. https:\/\/doi.org\/10.1145\/2463664.2465221","DOI":"10.1145\/2463664.2465221"},{"key":"6102_CR4","unstructured":"Baier, C., & Katoen, J. P. (2008). Principles of model checking (representation and mind series). The MIT Press."},{"key":"6102_CR5","doi-asserted-by":"crossref","unstructured":"Belardinelli, F., Lomuscio, A., & Patrizi, F. (2011). Verification of deployed artifact systems via data abstraction. In G. Kappel, Z. Maamar, & H. R. Motahari-Nezhad (Eds.), Service-oriented computing (pp. 142\u2013156). Springer.","DOI":"10.1007\/978-3-642-25535-9_10"},{"key":"6102_CR6","unstructured":"Belardinelli, F., Lomuscio, A., & Patrizi, F. (2012). An abstraction technique for the verification of artifact-centric systems. In Proceedings of the thirteenth international conference on principles of knowledge representation and reasoning, KR (pp. 319\u2013328). AAAI Press."},{"key":"6102_CR7","doi-asserted-by":"crossref","unstructured":"Belardinelli, F., Lomuscio, A., & Patrizi, F. (2013). Verification of agent-based artifact systems. CoRR. arXiv:1301.2678","DOI":"10.1613\/jair.4424"},{"key":"6102_CR8","unstructured":"Boutilier, C., Reiter, R., & Price, B. (2001). Symbolic dynamic programming for first-order mdps. In: Proceedings of the 17th international joint conference on artificial intelligence (vol. 1, pp. 690\u2013697). Morgan Kaufmann Publishers Inc. IJCAI\u201901. http:\/\/dl.acm.org\/citation.cfm?id=1642090.1642184"},{"key":"6102_CR9","doi-asserted-by":"publisher","unstructured":"Calvanese, D., Giacomo, G. D., Montali, M., & Patrizi, F. (2018). First-order $$\\mu$$-calculus over generic transition systems and applications to the situation calculus. Information and Computation, 259, 328 \u2013 347. https:\/\/doi.org\/10.1016\/j.ic.2017.08.007. 22nd International Symposium on Temporal Representation and Reasoning.","DOI":"10.1016\/j.ic.2017.08.007"},{"key":"6102_CR10","doi-asserted-by":"crossref","unstructured":"de Alfaro, L., & Roy, P. (2007). Magnifying-lens abstraction for Markov decision processes. In W. Damm & H. Hermanns (Eds.), Computer Aided Verification (pp. 325\u2013338). Springer.","DOI":"10.1007\/978-3-540-73368-3_38"},{"key":"6102_CR11","unstructured":"De Giacomo, G., Lesp\u00e9rance, Y., & Patrizi, F. (2012). Bounded situation calculus action theories and decidable verification. In Proc of KR 12."},{"key":"6102_CR12","unstructured":"De Giacomo, G., Lesp\u00e9rance, Y., & Patrizi, F. (2015). Bounded situation calculus action theories. CoRR. http:\/\/arxiv.org\/abs\/1509.02012"},{"key":"6102_CR13","doi-asserted-by":"crossref","unstructured":"De\u00a0Giacomo, G., Iocchi, L., Favorito, M., & Patrizi, F. (2019). Foundations for restraining bolts: Reinforcement learning with ltlf\/ldlf restraining specifications. Proceedings of the International Conference on Automated Planning and Scheduling, 29(1), 128\u2013136. https:\/\/ojs.aaai.org\/index.php\/ICAPS\/article\/view\/3549","DOI":"10.1609\/icaps.v29i1.3549"},{"key":"6102_CR46","unstructured":"de Salvo Braz, R., Amir, E., & Roth, D. (2005). Lifted first-order probabilistic inference. In: Proceedings of the 19th International Joint Conference on Artificial Intelligence (pp. 1319\u20131325). Edinburgh, Scotland. Morgan Kaufmann Publishers Inc. San Francisco"},{"issue":"2","key":"6102_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2200\/S00692ED1V01Y201601AIM032","volume":"10","author":"L De Raedt","year":"2016","unstructured":"De Raedt, L., Kersting, K., Natarajan, S., & Poole, D. (2016). Statistical relational artificial intelligence: Logic, probability, and computation. Synthesis Lectures on Artificial Intelligence and Machine Learning, 10(2), 1\u2013189. https:\/\/doi.org\/10.2200\/S00692ED1V01Y201601AIM032","journal-title":"Synthesis Lectures on Artificial Intelligence and Machine Learning"},{"key":"6102_CR15","doi-asserted-by":"crossref","unstructured":"Dehnert, C., Junges, S., Katoen, J. P., & Volk, M. (2017). A storm is coming: A modern probabilistic model checker. In R. Majumdar & V. Kun\u010dak (Eds.), Computer aided verification (pp. 592\u2013600). Springer.","DOI":"10.1007\/978-3-319-63390-9_31"},{"key":"6102_CR16","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1023\/B:MACH.0000039779.47329.3a","volume":"57","author":"K Driessens","year":"2004","unstructured":"Driessens, K., & D\u017eeroski, S. (2004). Integrating guidance into relational reinforcement learning. Machine Learning, 57, 271\u2013304. https:\/\/doi.org\/10.1023\/B:MACH.0000039779.47329.3a","journal-title":"Machine Learning"},{"issue":"1\u20132","key":"6102_CR17","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1007694015589","volume":"43","author":"S D\u017eeroski","year":"2001","unstructured":"D\u017eeroski, S., De Raedt, L., & Driessens, K. (2001). Relational Reinforcement Learning. Machine learning, 43(1\u20132), 7\u201352.","journal-title":"Machine learning"},{"key":"6102_CR18","unstructured":"Ferilli, S., Fanizzi, N., Mauro, N. D., & Basile, T. M. A. (2002). Efficient theta-subsumption under object identity. In In atti del workshop AI*IA su apprendimento automatico."},{"key":"6102_CR19","doi-asserted-by":"publisher","unstructured":"Forejt, V., Kwiatkowska, M., Norman, G., & Parker, D. (2011). Automated verification techniques for probabilistic systems (pp. 53\u2013113). Springer. https:\/\/doi.org\/10.1007\/978-3-642-21455-4_3","DOI":"10.1007\/978-3-642-21455-4_3"},{"key":"6102_CR20","doi-asserted-by":"crossref","unstructured":"Fulton, N., & Platzer, A. (2018). Safe reinforcement learning via formal methods: Toward safe control through proof and learning. In AAAI (pp. 6485\u20136492). https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/17376","DOI":"10.1609\/aaai.v32i1.12107"},{"key":"6102_CR21","unstructured":"Gabbay, D. M. (2003). Many-dimensional modal logics: Theory and applications. Elsevier North Holland."},{"key":"6102_CR22","first-page":"1437","volume":"16","author":"J Garcia","year":"2015","unstructured":"Garcia, J., & Fern\u00e1ndez, F. (2015). A comprehensive survey on safe reinforcement learning. Journal of Machine Learning Research, 16, 1437\u20131480.","journal-title":"Journal of Machine Learning Research"},{"key":"6102_CR23","unstructured":"Giacomo, G. D. (2019). Queryable self-deliberating dynamic systems. iJCAI. https:\/\/www.cse.ust.hk\/pg\/seminars\/S19\/giacomo.html"},{"key":"6102_CR24","doi-asserted-by":"crossref","unstructured":"Giunchiglia, F., & Traverso, P. (2000). Planning as model checking. In S. Biundo & M. Fox (Eds.), Recent advances in AI planning (pp. 1\u201320). Springer.","DOI":"10.1007\/10720246_1"},{"key":"6102_CR25","doi-asserted-by":"publisher","unstructured":"Haddad, S., & Monmege, B. (2014). Reachability in MDPs: Refining convergence of value iteration (Vol. 8762, pp. 125\u2013137). Springer. https:\/\/doi.org\/10.1007\/978-3-319-11439-2_10","DOI":"10.1007\/978-3-319-11439-2_10"},{"key":"6102_CR26","doi-asserted-by":"crossref","unstructured":"Hahn, E. M., Li, Y., Schewe, S., Turrini, A., & Zhang, L. (2014). IscasMC: A web-based probabilistic model checker (Vol. 8442, pp. 312\u2013317). Springer.","DOI":"10.1007\/978-3-319-06410-9_22"},{"key":"6102_CR27","doi-asserted-by":"crossref","unstructured":"Hasanbeig, M., Kantaros, Y., Abate, A., Kroening, D., Pappas, G. J., & Lee, I. (2019). Reinforcement learning for temporal logic controlsynthesis with probabilistic satisfaction guarantees. In 2019 IEEE 58th conference on decision and control (CDC) (pp. 5338\u20135343).","DOI":"10.1109\/CDC40024.2019.9028919"},{"key":"6102_CR28","doi-asserted-by":"publisher","unstructured":"He, K., Lahijanian, M., Kavraki, L. E., & Vardi, M. Y. (2015). Towards manipulation planning with temporal logic specifications. In 2015 IEEE international conference on robotics and automation (ICRA) (pp. 346\u2013352). https:\/\/doi.org\/10.1109\/ICRA.2015.7139022","DOI":"10.1109\/ICRA.2015.7139022"},{"key":"6102_CR29","doi-asserted-by":"publisher","unstructured":"Jansen, N., K\u00f6nighofer, B., Junges, S., Serban, A., & Bloem, R. (2020). Safe reinforcement learning using probabilistic shields. In I. Konnov, L. Kovacs (Eds.), 31st international conference on concurrency theory, CONCUR 2020, Schloss Dagstuhl\u2013Leibniz\u2013Zentrum fur informatik GmbH (pp. 31\u2013316). Dagstuhl Publishing. https:\/\/doi.org\/10.4230\/LIPIcs.CONCUR.2020.3","DOI":"10.4230\/LIPIcs.CONCUR.2020.3"},{"key":"6102_CR30","doi-asserted-by":"publisher","unstructured":"Kattenbelt, M., Kwiatkowska, M., Norman, G., & Parker, D. (2008). Game-based probabilistic predicate abstraction in prism. Electronic Notes in Theoretical Computer Science, 2203, 5\u201321, https:\/\/doi.org\/10.1016\/j.entcs.2008.11.016. Proceedings of the Sixth Workshop on Quantitative Aspects of Programming Languages (QAPL 2008).","DOI":"10.1016\/j.entcs.2008.11.016"},{"key":"6102_CR31","unstructured":"Kersting, K. (2012). Lifted probabilistic inference. In ECAI (pp. 33\u201338)."},{"key":"6102_CR32","doi-asserted-by":"crossref","unstructured":"Kersting, K., & De Raedt, L. (2004). Logical Markov decision programs and the convergence of logical td($$\\lambda$$). In R. Camacho, R. King, & A. Srinivasan (Eds.), Inductive logic programming (pp. 180\u2013197). Springer.","DOI":"10.1007\/978-3-540-30109-7_16"},{"key":"6102_CR33","doi-asserted-by":"publisher","unstructured":"Kersting, K., Otterlo, M. V., & De\u00a0Raedt, L. (2004). Bellman goes relational. In Proceedings of the 21st international conference on machine learning. ACM, ICML \u201904 (p. 59). https:\/\/doi.org\/10.1145\/1015330.1015401","DOI":"10.1145\/1015330.1015401"},{"key":"6102_CR34","doi-asserted-by":"crossref","unstructured":"Kwiatkowska, M., Norman, G., & Parker, D. (2011). In G. Gopalakrishnan & S. Qadeer (Eds.), PRISM 4.0: Verification of probabilistic real-time systems (Vol. 6806, pp. 585\u2013591). Springer.","DOI":"10.1007\/978-3-642-22110-1_47"},{"issue":"2","key":"6102_CR35","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1109\/TRO.2011.2172150","volume":"28","author":"M Lahijanian","year":"2012","unstructured":"Lahijanian, M., Andersson, S. B., & Belta, C. (2012). Temporal logic motion planning and control with probabilistic satisfaction guarantees. IEEE Transactions on Robotics, 28(2), 396\u2013409. https:\/\/doi.org\/10.1109\/TRO.2011.2172150","journal-title":"IEEE Transactions on Robotics"},{"key":"6102_CR36","doi-asserted-by":"crossref","unstructured":"Leonetti, M., Iocchi, L., & Patrizi, F. (2012). Automatic generation and learning of finite-state controllers. In A. Ramsay & G. Agre (Eds.), Artificial intelligence: Methodology, systems, and applications (pp. 135\u2013144). Springer.","DOI":"10.1007\/978-3-642-33185-5_15"},{"key":"6102_CR37","doi-asserted-by":"publisher","unstructured":"Maly, M. R., Lahijanian, M., Kavraki, L. E., Kress-Gazit, H., & Vardi, M. Y. (2013). Iterative temporal motion planning for hybrid systems in partially unknown environments. In Proceedings of the 16th international conference on hybrid systems: Computation and control, association for computing machinery (pp. 353\u2013362). HSCC \u201913. https:\/\/doi.org\/10.1145\/2461328.2461380","DOI":"10.1145\/2461328.2461380"},{"key":"6102_CR38","doi-asserted-by":"publisher","unstructured":"Marthi, B. (2007). Automatic shaping and decomposition of reward functions. In Proceedings of the 24th international conference on machine learning, association for computing machinery (pp. 601\u2013608). ICML \u201907. https:\/\/doi.org\/10.1145\/1273496.1273572","DOI":"10.1145\/1273496.1273572"},{"key":"6102_CR39","doi-asserted-by":"publisher","unstructured":"Mart\u00ednez, D., Aleny\u00e7, G., & Torras, C. (2017). Relational reinforcement learning with guided demonstrations. Artificial Intelligence, 247, 295 \u2013 312. https:\/\/doi.org\/10.1016\/j.artint.2015.02.006. Special Issue on AI and Robotics.","DOI":"10.1016\/j.artint.2015.02.006"},{"key":"6102_CR40","doi-asserted-by":"publisher","unstructured":"Mason, G., Calinescu, R., Kudenko, D., & Banks, A. (2018). Assurance in reinforcement learning using quantitative verification (pp. 71\u201396). Springer. https:\/\/doi.org\/10.1007\/978-3-319-66790-4_5","DOI":"10.1007\/978-3-319-66790-4_5"},{"key":"6102_CR41","doi-asserted-by":"publisher","unstructured":"McMillan, K. L. (1993). Symbolic model checking (pp. 25\u201360). Springer. https:\/\/doi.org\/10.1007\/978-1-4615-3190-6_3","DOI":"10.1007\/978-1-4615-3190-6_3"},{"key":"6102_CR42","doi-asserted-by":"crossref","unstructured":"Nienhuys-Cheng, S. H., & Wolf, R. (1997). Foundations of inductive logic programming. Springer.","DOI":"10.1007\/3-540-62927-0"},{"key":"6102_CR43","unstructured":"Otterlo, M. V. (2004). Reinforcement learning for relational MDPS. In Proceedings of the machine learning conference of Belgium and the Netherlands."},{"key":"6102_CR44","doi-asserted-by":"crossref","unstructured":"Pecka, M., & Svoboda, T. (2014). Safe exploration techniques for reinforcement learning\u2014An overview. In J. Hodicky (Ed.), Modelling and simulation for autonomous systems (pp. 357\u2013375). Springer.","DOI":"10.1007\/978-3-319-13823-7_31"},{"key":"6102_CR45","doi-asserted-by":"publisher","unstructured":"Roy, P., Parker, D., Norman, G., & De\u00a0Alfaro, L. (2008). Symbolic magnifying lens abstraction in Markov decision processes (pp. 3\u2013112). https:\/\/doi.org\/10.1109\/QEST.2008.41.","DOI":"10.1109\/QEST.2008.41"},{"key":"6102_CR47","doi-asserted-by":"publisher","unstructured":"Sanner, S., & Boutilier, C. (2009). Practical solution techniques for first-order mdps. Artificial Intelligence, 173(5), 748\u2013788. https:\/\/doi.org\/10.1016\/j.artint.2008.11.003. Advances in Automated Plan Generation","DOI":"10.1016\/j.artint.2008.11.003"},{"issue":"1","key":"6102_CR48","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/S0004-3702(00)00079-5","volume":"125","author":"J Slaney","year":"2001","unstructured":"Slaney, J., & Thi\u00e9baux, S. (2001). Blocks world revisited. Artificial Intelligence, 125(1), 119\u2013153. https:\/\/doi.org\/10.1016\/S0004-3702(00)00079-5","journal-title":"Artificial Intelligence"},{"key":"6102_CR49","doi-asserted-by":"crossref","unstructured":"Sprauel, J., Kolobov, A., & Teichteil-K\u00f6nigsbuch, F. (2014). Saturated path-constrained mdp: Planning under uncertainty and deterministic model-checking constraints. In 28th AAAI conference on artificial intelligence. AAAI Press. https:\/\/www.microsoft.com\/en-us\/research\/publication\/saturated-path-constrained-mdp-planning-uncertainty-deterministic-model-checking-constraints\/","DOI":"10.1609\/aaai.v28i1.9041"},{"key":"6102_CR50","unstructured":"Teichteil-K\u00f6nigsbuch, F. (2012). Path-Constrained Markov Decision Processes: bridging the gap between probabilistic model-checking and decision-theoretic planning. In 20th European conference on artificial intelligence (ECAI 2012). MONTPELLIER. https:\/\/hal-onera.archives-ouvertes.fr\/hal-01060349"},{"key":"6102_CR51","unstructured":"Van den Broeck, G., Taghipour, N., Meert, W., Davis, J., & De Raedt, L. (2011). Lifted probabilistic inference by first-order knowledge compilation. In Proceedings of the 22nd international joint conference on artificial intelligence, AAAI Press\/international joint conferences on artificial intelligence, Menlo (pp. 2178\u20132185)."},{"key":"6102_CR52","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1613\/jair.2489","volume":"31","author":"C Wang","year":"2008","unstructured":"Wang, C., Joshi, S., & Khardon, R. (2008). First order decision diagrams for relational MDPs. Journal of Artificial Intelligence Research, 31, 431\u2013472.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"6102_CR53","unstructured":"Yoon, S. W., Fern, A., & Givan, R. (2012). Inductive policy selection for first-order mdps. arXiv:1301.0614."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06102-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-021-06102-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06102-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T17:35:32Z","timestamp":1687541732000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-021-06102-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,23]]},"references-count":53,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["6102"],"URL":"https:\/\/doi.org\/10.1007\/s10994-021-06102-7","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,23]]},"assertion":[{"value":"19 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 October 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}