{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:24:27Z","timestamp":1779384267568,"version":"3.53.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3193494","type":"journal-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T19:57:08Z","timestamp":1658779028000},"page":"78148-78158","source":"Crossref","is-referenced-by-count":16,"title":["Learning and Assessing Optimal Dynamic Treatment Regimes Through Cooperative Imitation Learning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6390-1864","authenticated-orcid":false,"given":"Syed Ihtesham Hussain","family":"Shah","sequence":"first","affiliation":[{"name":"CNR, Institute for High Performance Computing and Networking (ICAR), Napoli, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8177-032X","authenticated-orcid":false,"given":"Antonio","family":"Coronato","sequence":"additional","affiliation":[{"name":"CNR, Institute for High Performance Computing and Networking (ICAR), Napoli, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0815-4883","authenticated-orcid":false,"given":"Muddasar","family":"Naeem","sequence":"additional","affiliation":[{"name":"CNR, Institute for High Performance Computing and Networking (ICAR), Napoli, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"De Pietro","sequence":"additional","affiliation":[{"name":"CNR, Institute for High Performance Computing and Networking (ICAR), Napoli, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-022513-115553"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101964"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/sim.2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2168260.2168266"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.104130"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116434"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/jsan11010013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-018-1108-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s40860-019-00084-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/s22010309"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3535-8_48"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114285"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3038605"},{"key":"ref14","article-title":"Continuous state-space models for optimal sepsis treatment\u2014A deep reinforcement learning approach","volume-title":"arXiv:1705.08422","author":"Raghu","year":"2017"},{"key":"ref15","article-title":"Deep reinforcement learning for sepsis treatment","volume-title":"arXiv:1711.09602","author":"Raghu","year":"2017"},{"key":"ref16","first-page":"101","article-title":"Learning agents for uncertain environments","volume-title":"Proc. 11th Annu. Conf. Comput. Learn.","author":"Russell"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_10"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1108\/17563781211255862"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00389"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9076-1_11"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780199754649.003.0013"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1093\/jrsssb\/qkad011"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498535"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3980837"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/bimj.202100077"},{"key":"ref27","article-title":"Learning optimal dynamic treatment regimes using causal tree methods in medicine","volume-title":"arXiv:2204.07124","author":"Bl\u00fcmlein","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/8952219"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-4-431-56922-0_8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219961"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098109"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref33","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1108\/17563781211255862"},{"key":"ref36","article-title":"On the performance of maximum likelihood inverse reinforcement learning","volume-title":"arXiv:1202.1558","author":"Ratia","year":"2012"},{"key":"ref37","first-page":"729","article-title":"Maximum margin planning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Bagnell"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2010.5581063"},{"key":"ref39","article-title":"Inverse reinforcement learning via deep Gaussian process","volume-title":"arXiv:1512.08065","author":"Jin","year":"2015"},{"key":"ref40","first-page":"4565","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3156\/jsoft.29.5_177_2"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3233\/AISE210097"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IE51775.2021.9486594"},{"key":"ref45","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. ICML","volume":"1","author":"Ng"},{"key":"ref46","article-title":"Learning to drive using inverse reinforcement learning and deep Q-networks","volume-title":"arXiv:1612.03653","author":"Sharifzadeh","year":"2016"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00026"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3233\/AISE210096"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380248"},{"key":"ref50","first-page":"8707","article-title":"Deep reinforcement learning with robust and smooth policy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shen"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1111\/1467-985x.00154"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1191\/1740774S04cn002oa"},{"key":"ref53","first-page":"11012","article-title":"Designing optimal dynamic treatment regimes: A causal reinforcement learning approach","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref54","article-title":"(More) efficient reinforcement learning via posterior sampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Osband"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1002\/cjs.11162"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09837927.pdf?arnumber=9837927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T10:42:47Z","timestamp":1706784167000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9837927\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3193494","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}