{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:33:57Z","timestamp":1740123237112,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T00:00:00Z","timestamp":1673481600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T00:00:00Z","timestamp":1673481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"crossref","award":["FA9550-19-1-0177"],"award-info":[{"award-number":["FA9550-19-1-0177"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Autom Reasoning"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s10817-022-09657-9","type":"journal-article","created":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T06:02:56Z","timestamp":1673503376000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimal Deterministic Controller Synthesis from Steady-State Distributions"],"prefix":"10.1007","volume":"67","author":[{"given":"Alvaro","family":"Velasquez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ismail","family":"Alkhouri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5821-5117","authenticated-orcid":false,"given":"K.","family":"Subramani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piotr","family":"Wojciechowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Atia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,12]]},"reference":[{"key":"9657_CR1","doi-asserted-by":"crossref","unstructured":"Akshay, S., Bertrand, N., Haddad, S., Helouet, L.: The steady-state control problem for Markov decision processes. In: International conference on quantitative evaluation of systems, pp 290\u2013304. Springer (2013)","DOI":"10.1007\/978-3-642-40196-1_26"},{"key":"9657_CR2","volume-title":"Constrained Markov Decision Processes","author":"E Altman","year":"1999","unstructured":"Altman, E.: Constrained Markov Decision Processes, vol. 7. CRC Press, Boca Raton (1999)"},{"key":"9657_CR3","volume-title":"Constrained Markov Decision Processes","author":"E Altman","year":"1999","unstructured":"Altman, E.: Constrained Markov Decision Processes, vol. 7. CRC Press, Boca Raton (1999)"},{"key":"9657_CR4","doi-asserted-by":"crossref","unstructured":"Atia, G.K., Beckus, A., Alkhouri, I., Velasquez, A.: Steady-state policy synthesis in multichain Markov decision processes. In: Proceedings of the 29th international joint conference on artificial intelligence (IJCAI), pp 4069\u20134075. International joint conferences on artificial intelligence organization, 7 (2020)","DOI":"10.24963\/ijcai.2020\/563"},{"key":"9657_CR5","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1613\/jair.1.12611","volume":"72","author":"GK Atia","year":"2021","unstructured":"Atia, G.K., Beckus, A., Alkhouri, I., Velasquez, A.: Steady-state planning in expected reward multichain MDPS. J. Artif. Intell. Res. 72, 1029\u20131082 (2021)","journal-title":"J. Artif. Intell. Res."},{"key":"9657_CR6","doi-asserted-by":"crossref","unstructured":"Baier, C., Haverkort, B, Hermanns, H., Katoen, J.-P.: Model checking continuous-time markov chains by transient analysis. In: International conference on computer aided verification, pp 358\u2013372. Springer (2000)","DOI":"10.1007\/10722167_28"},{"key":"9657_CR7","unstructured":"Baumgartner, P., Thi\u00e9baux, S., Trevizan, F.: Heuristic search planning with multi-objective probabilistic ltl constraints. In: Sixteenth international conference on principles of knowledge representation and reasoning (2018)"},{"issue":"3","key":"9657_CR8","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1007\/s10957-012-9989-5","volume":"153","author":"S Bhatnagar","year":"2012","unstructured":"Bhatnagar, S., Lakshmanan, K.: An online actor\u2013critic algorithm with function approximation for constrained Markov decision processes. J. Optim. Theory Appl. 153(3), 688\u2013708 (2012)","journal-title":"J. Optim. Theory Appl."},{"issue":"7","key":"9657_CR9","doi-asserted-by":"publisher","first-page":"1689","DOI":"10.1081\/STA-120037268","volume":"33","author":"M Boussemart","year":"2004","unstructured":"Boussemart, M., Limnios, N.: Markov decision processes with asymptotic average failure rate constraint. Commun. Stat. Theory Methods 33(7), 1689\u20131714 (2004)","journal-title":"Commun. Stat. Theory Methods"},{"issue":"1","key":"9657_CR10","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1081\/STM-120002780","volume":"18","author":"M Boussemart","year":"2002","unstructured":"Boussemart, M., Limnios, N., Fillion, J.C.: Non-ergodic Markov decision processes with a constraint on the asymptotic failure rate: general class of policies. Stoch. Models 18(1), 173\u2013191 (2002)","journal-title":"Stoch. Models"},{"issue":"1","key":"9657_CR11","doi-asserted-by":"publisher","first-page":"158","DOI":"10.2168\/LMCS-10(1:13)2014","volume":"10","author":"T Br\u00e1zdil","year":"2014","unstructured":"Br\u00e1zdil, T., Brozek, V., Chatterjee, K., Forejt, V., Kucera, A.: Two views on multiple mean-payoff objectives in Markov decision processes. Log. Methods Comput. Sci. 10(1), 158 (2014)","journal-title":"Log. Methods Comput. Sci."},{"key":"9657_CR12","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., Zaremba, W.: Openai gym. (2016) arXiv preprint arXiv:1606.01540"},{"key":"9657_CR13","doi-asserted-by":"crossref","unstructured":"Camacho, A., McIlraith, S.A.: Strong fully observable non-deterministic planning with ltl and ltlf goals. In: Proceedings of the twenty-eighth international joint conference on artificial intelligence, IJCAI-19, pp 5523\u20135531. International joint conferences on artificial intelligence organization, 7 (2019)","DOI":"10.24963\/ijcai.2019\/767"},{"issue":"2","key":"9657_CR14","first-page":"258","volume":"113","author":"K Chatterjee","year":"2017","unstructured":"Chatterjee, K., Kret\u00ednsk, Z., Kret\u00ednsk\u00fd, J.: Unifying two views on multiple mean-payoff objectives in Markov decision processes. Log. Methods Comput. Sci. 113(2), 258 (2017)","journal-title":"Log. Methods Comput. Sci."},{"key":"9657_CR15","volume-title":"Papadimitriou: Computational Complexity","author":"H Christos","year":"1994","unstructured":"Christos, H.: Papadimitriou: Computational Complexity. Addison-Wesley, New York (1994)"},{"issue":"4","key":"9657_CR16","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1145\/210332.210339","volume":"42","author":"C Courcoubetis","year":"1995","unstructured":"Courcoubetis, C., Yannakakis, M.: The complexity of probabilistic verification. J. ACM 42(4), 857\u2013907 (1995)","journal-title":"J. ACM"},{"issue":"2","key":"9657_CR17","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1080\/17442508.2014.939979","volume":"87","author":"F Dufour","year":"2015","unstructured":"Dufour, F., Prieto-Rumeau, T.: Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities. Stochast. Int. J. Probab. Stoch. Process. 87(2), 273\u2013307 (2015)","journal-title":"Stochast. Int. J. Probab. Stoch. Process."},{"key":"9657_CR18","unstructured":"Engesser, T., Bolander, T., Nebel, B.: Cooperative epistemic multi-agent planning with implicit coordination. In: Distributed and multi-agent planning (DMAP-15), p 68"},{"key":"9657_CR19","doi-asserted-by":"publisher","first-page":"4","DOI":"10.2168\/LMCS-4(4:8)2008","volume":"4","author":"K Etessami","year":"2008","unstructured":"Etessami, K., Kwiatkowska, M.Z., Vardi, M.Y., Yannakakis, M.: Multi-objective model checking of Markov decision processes. Log. Methods Comput. Sci. 4, 4 (2008)","journal-title":"Log. Methods Comput. Sci."},{"issue":"12","key":"9657_CR20","doi-asserted-by":"publisher","first-page":"4051","DOI":"10.1109\/TAC.2018.2799561","volume":"63","author":"M Guo","year":"2018","unstructured":"Guo, M., Zavlanos, M.M.: Probabilistic motion planning under temporal tasks and soft constraints. IEEE Trans. Autom. Control 63(12), 4051\u20134066 (2018)","journal-title":"IEEE Trans. Autom. Control"},{"key":"9657_CR21","unstructured":"Ibm ilog cplex optimization studio v12.8.0 documentation. IBM Knowledge Center (2017)"},{"key":"9657_CR22","volume-title":"Linear Programming and Finite Markovian Control Problems","author":"LCM Kallenberg","year":"1983","unstructured":"Kallenberg, L.C.M.: Linear Programming and Finite Markovian Control Problems. Mathematisch Centrum, Amsterdam (1983)"},{"key":"9657_CR23","unstructured":"Kazemi, M., Perez, M., Somenzi, F., Soudjani, S., Trivedi, A., Velasquez, A.: Translating omega-regular specifications to average objectives for model-free reinforcement learning. In: Proceedings of the 21st international conference on autonomous agents and multiagent systems, pp 732\u2013741 (2022)"},{"key":"9657_CR24","unstructured":"Konstantopoulos, T: Markov Chains and Random Walks. Lecture notes (2009)"},{"issue":"1","key":"9657_CR25","doi-asserted-by":"publisher","first-page":"15","DOI":"10.4271\/2016-01-0128","volume":"4","author":"P Koopman","year":"2016","unstructured":"Koopman, P., Wagner, M.: Challenges in autonomous vehicle testing and validation. SAE Int. J. Transp. Saf. 4(1), 15\u201324 (2016)","journal-title":"SAE Int. J. Transp. Saf."},{"issue":"3","key":"9657_CR26","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1287\/moor.27.3.545.316","volume":"27","author":"Dmitry Krass","year":"2002","unstructured":"Krass, Dmitry, Vrieze, O.J.: Achieving target state-action frequencies in multichain average-reward Markov decision processes. Math. Oper. Res. 27(3), 545\u2013566 (2002)","journal-title":"Math. Oper. Res."},{"key":"9657_CR27","doi-asserted-by":"crossref","unstructured":"K\u0159et\u00ednsk\u1ef3, J.: Ltl-constrained steady-state policy synthesis. (2021) arXiv preprint arXiv:2105.14894","DOI":"10.24963\/ijcai.2021\/565"},{"key":"9657_CR28","doi-asserted-by":"crossref","unstructured":"Kwiatkowska, M., Parker, D.: Automated verification and strategy synthesis for probabilistic systems. In: Automated technology for verification and analysis, pp 5\u201322. Springer (2013)","DOI":"10.1007\/978-3-319-02444-8_2"},{"key":"9657_CR29","doi-asserted-by":"crossref","unstructured":"Lakshmanan, K., Bhatnagar, S.: A novel q-learning algorithm with function approximation for constrained Markov decision processes. In 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp 400\u2013405. IEEE (2012)","DOI":"10.1109\/Allerton.2012.6483246"},{"issue":"11","key":"9657_CR30","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1109\/TAC.1983.1103166","volume":"28","author":"Andreas Lazar","year":"1983","unstructured":"Lazar, Andreas: Optimal flow control of a class of queueing networks in equilibrium. IEEE Trans. Automatic Control 28(11), 1001\u20131007 (1983)","journal-title":"IEEE Trans. Automatic Control"},{"key":"9657_CR31","doi-asserted-by":"crossref","unstructured":"Medina Ayala, A.I., Andersson, S.B., Belta, C.: Probabilistic control from time-bounded temporal logic specifications in dynamic environments. In: 2012 IEEE international conference on robotics and automation, pp 4705\u20134710. IEEE (2012)","DOI":"10.1109\/ICRA.2012.6224963"},{"key":"9657_CR32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511810633","volume-title":"Markov Chains","author":"JR Norris","year":"1997","unstructured":"Norris, J.R.: Markov Chains. Cambridge University Press, Cambridge (1997)"},{"issue":"7","key":"9657_CR33","doi-asserted-by":"publisher","first-page":"1804","DOI":"10.1016\/j.jcta.2013.06.008","volume":"120","author":"Igor Pak","year":"2013","unstructured":"Pak, Igor, Yang, Jed: Tiling simply connected regions with rectangles. J. Combinat. Theory Ser. A 120(7), 1804\u20131816 (2013)","journal-title":"J. Combinat. Theory Ser. A"},{"key":"9657_CR34","unstructured":"Pistore, M., Bettin, R., Traverso, P.: Symbolic techniques for planning with extended goals in non-deterministic domains. In: Sixth European conference on planning (2014)"},{"key":"9657_CR35","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes : Discrete Stochastic Dynamic Programming","author":"Martin Puterman","year":"1994","unstructured":"Puterman, Martin: Markov Decision Processes\u202f: Discrete Stochastic Dynamic Programming. Wiley, New York (1994)"},{"key":"9657_CR36","doi-asserted-by":"crossref","unstructured":"Saldi, N.: Finite-state approximations to discounted and average cost constrained Markov decision processes. IEEE Transactions on Automatic Control (2019)","DOI":"10.1109\/TAC.2018.2890756"},{"key":"9657_CR37","unstructured":"Sarathy, V., Kasenberg, D.l, Goel, S., Sinapov, J., Scheutz, M.: Spotter: extending symbolic planning operators through targeted reinforcement learning. In: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems, pp 1118\u20131126 (2021)"},{"key":"9657_CR38","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1146\/annurev-control-060117-105157","volume":"1","author":"W Schwarting","year":"2018","unstructured":"Schwarting, W., Alonso-Mor, J., Rus, D.: Planning and decision-making for autonomous vehicles. Robot. Autonom. Syst. Ann. Rev. Control 1, 187\u2013210 (2018)","journal-title":"Robot. Autonom. Syst. Ann. Rev. Control"},{"key":"9657_CR39","unstructured":"Song, L., Feng, Y. Zhang, L.: Planning for stochastic games with co-safe objectives. In: Twenty-fourth international joint conference on artificial intelligence (2015)"},{"key":"9657_CR40","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT Press, Cambridge (1998)"},{"key":"9657_CR41","unstructured":"Teichteil-K\u00f6nigsbuch, F.: 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) (2012)"},{"key":"9657_CR42","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1613\/jair.1676","volume":"25","author":"S Thi\u00e9baux","year":"2006","unstructured":"Thi\u00e9baux, S., Gretton, C., Slaney, J., Price, D., Kabanza, F.: Decision-theoretic planning with non-markovian rewards. J. Artif. Intell. Res. 25, 17\u201374 (2006)","journal-title":"J. Artif. Intell. Res."},{"key":"9657_CR43","doi-asserted-by":"crossref","unstructured":"Trevizan, F.W, Thi\u00e9baux, S., Santana, P.H., Williams, B.C.: Heuristic search in dual space for constrained stochastic shortest path problems. In: ICAPS, pp 326\u2013334 (2016)","DOI":"10.1609\/icaps.v26i1.13768"},{"key":"9657_CR44","doi-asserted-by":"crossref","unstructured":"Velasquez, A.: Steady-state policy synthesis for verifiable control. In: Proceedings of the twenty-eighth international joint conference on artificial intelligence, IJCAI-19, pp. 5653\u20135661. International Joint Conferences on Artificial Intelligence Organization, 7 (2019)","DOI":"10.24963\/ijcai.2019\/784"},{"key":"9657_CR45","unstructured":"Wan, Y., Naik, A., Sutton, R.S.: Learning and planning in average-reward markov decision processes. In: International Conference on Machine Learning, pp 10653\u201310662. PMLR (2021)"}],"container-title":["Journal of Automated Reasoning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10817-022-09657-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10817-022-09657-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10817-022-09657-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T09:23:27Z","timestamp":1679649807000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10817-022-09657-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,12]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["9657"],"URL":"https:\/\/doi.org\/10.1007\/s10817-022-09657-9","relation":{},"ISSN":["0168-7433","1573-0670"],"issn-type":[{"type":"print","value":"0168-7433"},{"type":"electronic","value":"1573-0670"}],"subject":[],"published":{"date-parts":[[2023,1,12]]},"assertion":[{"value":"27 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"7"}}