{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:32:02Z","timestamp":1786980722098,"version":"build-2736575974"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100009024","name":"Exploratory Research for Advanced Technology","doi-asserted-by":"publisher","award":["JPMJER1603"],"award-info":[{"award-number":["JPMJER1603"]}],"id":[{"id":"10.13039\/501100009024","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s10458-023-09607-8","type":"journal-article","created":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:02:25Z","timestamp":1701820945000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Uniformly constrained reinforcement learning"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4390-7676","authenticated-orcid":false,"given":"Jaeyoung","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2903-0823","authenticated-orcid":false,"given":"Sean","family":"Sedwards","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1642-1101","authenticated-orcid":false,"given":"Krzysztof","family":"Czarnecki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,12,6]]},"reference":[{"key":"9607_CR1","unstructured":"Achiam, J., Held, D., Tamar, A., & Abbeel, P. (2017). Constrained policy optimization. In D. Precup & Y. W. Teh (Eds.), 34th international conference on machine learning. Proceedings of machine learning research (Vol. 70, pp. 22\u201331). MLR Press."},{"key":"9607_CR2","doi-asserted-by":"publisher","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., et al. (2018). Safe reinforcement learning via shielding. In 32nd AAAI conference on artificial intelligence (Vol. 32, No. 1, pp. 2669\u20132678). https:\/\/doi.org\/10.1609\/aaai.v32i1.11797. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/11797.","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"9607_CR3","volume-title":"Constrained Markov decision processes","author":"E Altman","year":"1999","unstructured":"Altman, E. (1999). Constrained Markov decision processes. Boca Raton: CRC Press."},{"key":"9607_CR4","unstructured":"Boutilier, C., & Lu, T. (2016). Budget allocation using weakly coupled, constrained Markov decision processes. In Proceedings of the 32nd conference on uncertainty in artificial intelligence (pp. 52\u201361)."},{"key":"9607_CR5","unstructured":"Carrara, N., Leurent, E., Laroche, R., et al. (2019). Budgeted reinforcement learning in continuous state space. In Advances in neural information processing systems (Vol. 32). Curran Associates, Inc."},{"key":"9607_CR6","doi-asserted-by":"publisher","unstructured":"Chen, R. C., & Feinberg, E. A. (2007). Non-randomized policies for constrained Markov decision processes. In Mathematical methods of operations research (Vol. 66, pp. 165\u2013179). https:\/\/doi.org\/10.1007\/s00186-006-0133-x.","DOI":"10.1007\/s00186-006-0133-x"},{"key":"9607_CR7","unstructured":"Chow, Y., Nachum, O., Duenez-Guzman, E., & Ghavamzadeh, M. (2018). A Lyapunov based approach to safe reinforcement learning. In Advances in neural information processing systems (NeurIPS) (Vol. 31, pp. 8103\u20138112). OpenReview."},{"key":"9607_CR8","unstructured":"Dolgov, D., & Durfee, E. (2005). Stationary deterministic policies for constrained MDPs with multiple rewards, costs, and discount factors. In Proceedings of the 19th international joint conference on artificial intelligence. IJCAI (pp. 1326\u20131331). Morgan Kaufmann."},{"issue":"1","key":"9607_CR9","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1287\/moor.25.1.130.15210","volume":"25","author":"EA Feinberg","year":"2000","unstructured":"Feinberg, E. A. (2000). Constrained discounted Markov decision processes and Hamiltonian cycles. Mathematics of Operations Research, 25(1), 130\u2013140.","journal-title":"Mathematics of Operations Research"},{"issue":"3","key":"9607_CR10","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1109\/9.751365","volume":"44","author":"EA Feinberg","year":"1999","unstructured":"Feinberg, E. A., & Shwartz, A. (1999). Constrained dynamic programming with two discount factors: applications and an algorithm. IEEE Transactions on Automatic Control, 44(3), 628\u2013631.","journal-title":"IEEE Transactions on Automatic Control"},{"key":"9607_CR11","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1007\/978-3-642-19835-9_11","volume-title":"Tools and algorithms for the construction and analysis of systems","author":"V Forejt","year":"2011","unstructured":"Forejt, V., Kwiatkowska, M., Norman, G., Parker, D., & Qu, H. (2011). Quantitative multi-objective verification for probabilistic systems. In P. A. Abdulla & K. R. M. Leino (Eds.), Tools and algorithms for the construction and analysis of systems (pp. 112\u2013127). Berlin: Springer."},{"key":"9607_CR12","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/978-3-642-33386-6_25","volume-title":"Automated technology for verification and analysis","author":"V Forejt","year":"2012","unstructured":"Forejt, V., Kwiatkowska, M., & Parker, D. (2012). Pareto curves for probabilistic model checking. In S. Chakraborty & M. Mukund (Eds.), Automated technology for verification and analysis (pp. 317\u2013332). Berlin: Springer."},{"issue":"42","key":"9607_CR13","first-page":"1437","volume":"16","author":"J Gar\u00eda","year":"2015","unstructured":"Gar\u00eda, J., & Fern\u00e1ndez, F. (2015). A comprehensive survey on safe reinforcement learning. Journal of Machine Learning Research, 16(42), 1437\u20131480.","journal-title":"Journal of Machine Learning Research"},{"key":"9607_CR14","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1613\/jair.1666","volume":"24","author":"P Geibel","year":"2005","unstructured":"Geibel, P., & Wysotzki, F. (2005). Risk-sensitive reinforcement learning applied to control under constraints. Journal of Artificial Intelligence Research, 24, 81\u2013108.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"9607_CR15","doi-asserted-by":"publisher","unstructured":"Hahn,J., & Zoubir, A. M. (2016). Risk-sensitive decision making via constrained expected returns. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 2569\u20132573). https:\/\/doi.org\/10.1109\/ICASSP.2016.7472141.","DOI":"10.1109\/ICASSP.2016.7472141"},{"key":"9607_CR16","unstructured":"Kalweit, G., Huegle, M., Werling, M., & Boedecker, J. (2020). Deep constrained Q-learning. arXiv:2003.09398."},{"key":"9607_CR17","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/978-3-030-30281-8_20","volume-title":"Quantitative evaluation of systems","author":"J Lee","year":"2019","unstructured":"Lee, J., Balakrishnan, A., Gaurav, A., Czarnecki, K., & Sedwards, S. (2019). WiseMove: A framework to investigate safe deep reinforcement learning for autonomous driving. In D. Parker & V. Wolf (Eds.), Quantitative evaluation of systems (pp. 350\u2013354). Cham: Springer."},{"key":"9607_CR18","unstructured":"Lee, J. , Sedwards, S., & Czarnecki, K. (2021). Recursive constraints to prevent instability in constrained reinforcement learning. In Hayes, Mannion, & Vamplew (Eds.), Proceedings of 1st multi-objective decision making workshop (MODeM 2021). http:\/\/modem2021.cs.nuigalway.ie. arXiv:2201.07958."},{"key":"9607_CR19","unstructured":"Lee, S. Y., Sungik, C., & Chung, S.-Y. (2019). Sample-efficient deep reinforcement learning via episodic backward update. In Advances in neural information processing systems (Vol. 32). Curran Associates, Inc."},{"key":"9607_CR20","volume-title":"Nonlinear multiobjective optimization","author":"K Miettinen","year":"1999","unstructured":"Miettinen, K. (1999). Nonlinear multiobjective optimization (Vol. 12). Berlin: Springer."},{"key":"9607_CR21","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes: Discrete stochastic dynamic programming","author":"ML Puterman","year":"1994","unstructured":"Puterman, M. L. (1994). Markov decision processes: Discrete stochastic dynamic programming. New York: Wiley."},{"key":"9607_CR22","doi-asserted-by":"publisher","unstructured":"Shalev-Shwartz, S., Shammah, S., & Shashua, A. (2016). Safe, multi-agent, reinforcement learning for autonomous driving. arXiv:1610.03295. https:\/\/doi.org\/10.48550\/ARXIV.1610.03295. arXiv:1610.03295.","DOI":"10.48550\/ARXIV.1610.03295"},{"issue":"1","key":"9607_CR23","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1023\/A:1018012322525","volume":"22","author":"SP Singh","year":"1996","unstructured":"Singh, S. P., & Sutton, R. S. (1996). Reinforcement learning with replacing eligibility traces. Machine Learning, 22(1), 123\u2013158. https:\/\/doi.org\/10.1023\/A:1018012322525","journal-title":"Machine Learning"},{"key":"9607_CR24","volume-title":"Reinforcement learning: An introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. Cambridge: MIT Press."},{"key":"9607_CR25","unstructured":"Tessler, C., Mankowitz, D. J., & Mannor, S. (2019). Reward constrained policy optimization. In International conference on learning representations (ICLR). OpenReview."},{"key":"9607_CR26","unstructured":"Undurti, A., Geramifard, A., & How, J. P. (2011). Function approximation for continuous constrained MDPs. Technical report, MIT. https:\/\/people.csail.mit.edu\/agf\/Files\/11ICRA-LinearCMDP.pdf."}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-023-09607-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10458-023-09607-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-023-09607-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T19:41:39Z","timestamp":1719862899000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10458-023-09607-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,6]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["9607"],"URL":"https:\/\/doi.org\/10.1007\/s10458-023-09607-8","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,6]]},"assertion":[{"value":"23 March 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"1"}}