{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T07:04:31Z","timestamp":1784012671576,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234431","type":"print"},{"value":"9789819234448","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3444-8_45","type":"book-chapter","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T06:16:14Z","timestamp":1784009774000},"page":"546-558","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Risk-Aware Safe Reinforcement Learning with CVaR-Based Constraints"],"prefix":"10.1007","author":[{"given":"Tianyu","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaorong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangfeng","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"45_CR1","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1631\/FITEE.1601650","volume":"18","author":"T Zhang","year":"2017","unstructured":"Zhang, T., et al.: Current trends in the development of intelligent unmanned autonomous systems. Front. Inf. Technol. Electron. Eng. 18, 68\u201385 (2017)","journal-title":"Front. Inf. Technol. Electron. Eng."},{"key":"45_CR2","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature. 575, 350\u2013354 (2019)","journal-title":"Nature"},{"key":"45_CR3","unstructured":"Raghu, A., et al.: Deep reinforcement learning for sepsis treatment. arXiv preprint arXiv:1711.09602. (2017)"},{"key":"45_CR4","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223","volume-title":"Constrained Markov Decision Processes","author":"E Altman","year":"2021","unstructured":"Altman, E.: Constrained Markov Decision Processes. Routledge (2021)"},{"key":"45_CR5","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2014","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. John Wiley & Sons (2014)"},{"key":"45_CR6","doi-asserted-by":"publisher","first-page":"11216","DOI":"10.1109\/TPAMI.2024.3457538","volume":"46","author":"S Gu","year":"2024","unstructured":"Gu, S., et al.: A review of safe reinforcement learning: methods, theories, and applications. IEEE Trans. Pattern Anal. Mach. Intell. 46, 11216\u201311235 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"45_CR7","doi-asserted-by":"publisher","first-page":"21","DOI":"10.21314\/JOR.2000.038","volume":"2","author":"RT Rockafellar","year":"2000","unstructured":"Rockafellar, R.T., Uryasev, S.: Optimization of conditional value-at-risk. J. Risk. 2, 21\u201342 (2000)","journal-title":"J. Risk"},{"key":"45_CR8","first-page":"1861","volume-title":"International Conference on Machine Learning","author":"T Haarnoja","year":"2018","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"45_CR9","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"N Fulton","year":"2018","unstructured":"Fulton, N., Platzer, A.: Safe reinforcement learning via formal methods: Toward safe control through proof and learning. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)"},{"key":"45_CR10","doi-asserted-by":"crossref","unstructured":"Yang, W.-C., Marra, G., Rens, G., De Raedt, L.: Safe reinforcement learning via probabilistic logic shields. arXiv preprint arXiv:2303.03226. (2023)","DOI":"10.24963\/ijcai.2023\/637"},{"key":"45_CR11","doi-asserted-by":"publisher","first-page":"6059","DOI":"10.1109\/CDC.2018.8619572","volume-title":"2018 IEEE Conference on Decision and Control (CDC)","author":"T Koller","year":"2018","unstructured":"Koller, T., Berkenkamp, F., Turchetta, M., Krause, A.: Learning-based model predictive control for safe exploration. In: 2018 IEEE Conference on Decision and Control (CDC), pp. 6059\u20136066. IEEE (2018)"},{"key":"45_CR12","unstructured":"Chow, Y., Nachum, O., Faust, A., Duenez-Guzman, E., Ghavamzadeh, M.: Lyapunov-based safe policy optimization for continuous control. arXiv preprint arXiv:1901.10031. (2019)"},{"key":"45_CR13","unstructured":"Ha, S., Xu, P., Tan, Z., Levine, S., Tan, J.: Learning to walk in the real world with minimal human effort. arXiv preprint arXiv:2002.08550. (2020)"},{"key":"45_CR14","first-page":"22","volume-title":"International Conference on Machine Learning","author":"J Achiam","year":"2017","unstructured":"Achiam, J., Held, D., Tamar, A., Abbeel, P.: Constrained policy optimization. In: International Conference on Machine Learning, pp. 22\u201331. PMLR (2017)"},{"key":"45_CR15","doi-asserted-by":"publisher","first-page":"9111","DOI":"10.52202\/068431-0662","volume":"35","author":"L Yang","year":"2022","unstructured":"Yang, L., et al.: Constrained update projection approach to safe policy optimization. Adv. Neural Inf. Proces. Syst. 35, 9111\u20139124 (2022)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"45_CR16","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1007\/s10994-022-06187-8","volume":"112","author":"Q Yang","year":"2023","unstructured":"Yang, Q., Sim\u00e3o, T.D., Tindemans, S.H., Spaan, M.T.: Safety-constrained reinforcement learning with a distributional safety critic. Mach. Learn. 112, 859\u2013887 (2023)","journal-title":"Mach. Learn."},{"key":"45_CR17","first-page":"70","volume":"2","author":"V Khokhlov","year":"2016","unstructured":"Khokhlov, V.: Conditional value-at-risk for elliptical distributions. Evropsk\u00fd \u010dasopis ekonomiky a managementu. 2, 70\u201379 (2016)","journal-title":"Evropsk\u00fd \u010dasopis ekonomiky a managementu"},{"key":"45_CR18","first-page":"1352","volume-title":"International Conference on Machine Learning","author":"T Haarnoja","year":"2017","unstructured":"Haarnoja, T., Tang, H., Abbeel, P., Levine, S.: Reinforcement learning with deep energy-based policies. In: International Conference on Machine Learning, pp. 1352\u20131361. PMLR (2017)"},{"key":"45_CR19","doi-asserted-by":"publisher","first-page":"18964","DOI":"10.52202\/075280-0831","volume":"36","author":"J Ji","year":"2023","unstructured":"Ji, J., et al.: Safety gymnasium: a unified safe reinforcement learning benchmark. Adv. Neural Inf. Proces. Syst. 36, 18964\u201318993 (2023)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"45_CR20","first-page":"1","volume":"25","author":"J Ji","year":"2024","unstructured":"Ji, J., et al.: Omnisafe: an infrastructure for accelerating safe reinforcement learning research. J. Mach. Learn. Res. 25, 1\u20136 (2024)","journal-title":"J. Mach. Learn. Res."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3444-8_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T06:16:17Z","timestamp":1784009777000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3444-8_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"ISBN":["9789819234431","9789819234448"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3444-8_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"assertion":[{"value":"15 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}