{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T10:34:42Z","timestamp":1742985282208,"version":"3.40.3"},"publisher-location":"Cham","reference-count":8,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030183042"},{"type":"electronic","value":"9783030183059"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-18305-9_68","type":"book-chapter","created":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T14:15:30Z","timestamp":1558361730000},"page":"605-608","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Safe Policy Learning with Constrained Return Variance"],"prefix":"10.1007","author":[{"given":"Arushi","family":"Jain","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,4,24]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Bacon, P.L., Harb, J., Precup, D.: The option-critic architecture. In: AAAI, pp. 1726\u20131734 (2017)","key":"68_CR1","DOI":"10.1609\/aaai.v31i1.10916"},{"unstructured":"Jain, A., Khetarpal, K., Precup, D.: Safe option-critic: Learning safety in the option-critic architecture. arXiv preprint arXiv:1807.08060 (2018)","key":"68_CR2"},{"unstructured":"Prashanth, L., Ghavamzadeh, M.: Actor-critic algorithms for risk-sensitive MDPs. In: Advances in Neural Information Processing Systems, pp. 252\u2013260 (2013)","key":"68_CR3"},{"issue":"3","key":"68_CR4","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1527\/tjsai.16.353","volume":"16","author":"M Sato","year":"2001","unstructured":"Sato, M., Kimura, H., Kobayashi, S.: TD algorithm for the variance of return and mean-variance reinforcement learning. Trans. Jpn. Soc. Artif. Intell. 16(3), 353\u2013362 (2001)","journal-title":"Trans. Jpn. Soc. Artif. Intell."},{"unstructured":"Sherstan, C., et al.: Directly estimating the variance of the $$\\lambda $$-return using temporal-difference methods. arXiv preprint arXiv:1801.08287 (2018)","key":"68_CR5"},{"unstructured":"Tamar, A., Di Castro, D., Mannor, S.: Policy gradients with variance related risk criteria. In: Proceedings of the Twenty-ninth International Conference on Machine Learning, pp. 387\u2013396 (2012)","key":"68_CR6"},{"issue":"13","key":"68_CR7","first-page":"1","volume":"17","author":"A Tamar","year":"2016","unstructured":"Tamar, A., Di Castro, D., Mannor, S.: Learning the variance of the reward-to-go. J. Mach. Learn. Res. 17(13), 1\u201336 (2016)","journal-title":"J. Mach. Learn. Res."},{"unstructured":"Tamar, A., Xu, H., Mannor, S.: Scaling up robust MDPs by reinforcement learning. arXiv preprint arXiv:1306.6189 (2013)","key":"68_CR8"}],"container-title":["Lecture Notes in Computer Science","Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-18305-9_68","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T18:59:22Z","timestamp":1710269962000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-18305-9_68"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030183042","9783030183059"],"references-count":8,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-18305-9_68","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"24 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Canadian AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canadian Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kingston, ON","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 May 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 May 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"canadianai2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.caiac.ca\/en\/conferences\/canadianai-2019\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}