{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T20:25:35Z","timestamp":1744835135365},"publisher-location":"New York, NY, USA","reference-count":7,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,17]],"date-time":"2019-06-17T00:00:00Z","timestamp":1560729600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,17]]},"DOI":"10.1145\/3328526.3329565","type":"proceedings-article","created":{"date-parts":[[2019,6,21]],"date-time":"2019-06-21T12:45:07Z","timestamp":1561121107000},"update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Learning in Structured MDPs with Convex Cost Functions"],"prefix":"10.1145","author":[{"given":"Shipra","family":"Agrawal","sequence":"first","affiliation":[{"name":"Columbia University, New York, NY, USA"}]},{"given":"Randy","family":"Jia","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, USA"}]}],"member":"320","published-online":{"date-parts":[[2019,6,17]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Alekh Agarwal Dean P Foster Daniel J Hsu Sham M Kakade and Alexander Rakhlin. 2011. Stochastic convex optimization with bandit feedback. In Advances in Neural Information Processing Systems. 1035--1043. Alekh Agarwal Dean P Foster Daniel J Hsu Sham M Kakade and Alexander Rakhlin. 2011. Stochastic convex optimization with bandit feedback. In Advances in Neural Information Processing Systems. 1035--1043."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2011.02.004"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1080.0367"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1080.0945"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1859902"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1040.0130"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Huanan Zhang Xiuli Chao and Cong Shi. 2017. Closing the Gap: A Learning Algorithm for the Lost-Sales Inventory System with Lead Times. (2017). Huanan Zhang Xiuli Chao and Cong Shi. 2017. Closing the Gap: A Learning Algorithm for the Lost-Sales Inventory System with Lead Times. (2017).","DOI":"10.2139\/ssrn.2922820"}],"event":{"name":"EC '19: ACM Conference on Economics and Computation","location":"Phoenix AZ USA","acronym":"EC '19","sponsor":["SIGecom Special Interest Group on Economics and Computation"]},"container-title":["Proceedings of the 2019 ACM Conference on Economics and Computation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3328526.3329565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T01:55:56Z","timestamp":1673229356000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3328526.3329565"}},"subtitle":["Improved Regret Bounds for Inventory Management"],"short-title":[],"issued":{"date-parts":[[2019,6,17]]},"references-count":7,"alternative-id":["10.1145\/3328526.3329565","10.1145\/3328526"],"URL":"https:\/\/doi.org\/10.1145\/3328526.3329565","relation":{},"subject":[],"published":{"date-parts":[[2019,6,17]]},"assertion":[{"value":"2019-06-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}