{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T05:51:04Z","timestamp":1769061064273,"version":"3.49.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9683076","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"1542-1547","source":"Crossref","is-referenced-by-count":9,"title":["Non-Markovian Reinforcement Learning using Fractional Dynamics"],"prefix":"10.1109","author":[{"given":"Gaurav","family":"Gupta","sequence":"first","affiliation":[{"name":"Univ. of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,USA"}]},{"given":"Chenzhong","family":"Yin","sequence":"additional","affiliation":[{"name":"Univ. of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,USA"}]},{"given":"Jyotirmoy V.","family":"Deshmukh","sequence":"additional","affiliation":[{"name":"Univ. of Southern California,Department of Computer Science,Los Angeles,CA,USA"}]},{"given":"Paul","family":"Bogdan","sequence":"additional","affiliation":[{"name":"Univ. of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,USA"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Reinforcement learning for joint optimization of multiple rewards","author":"agarwal","year":"2021"},{"key":"ref32","article-title":"Reinforcement learning with non-markovian rewards","author":"gaon","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/353"},{"key":"ref30","article-title":"Nonparametric general reinforcement learning","author":"leike","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref34","article-title":"Non-markovian control with gated end-to-end memory policy networks","author":"perez","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2010.00012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2016.7852369"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430866"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-61725-7_35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS.2018.00034"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8815074"},{"key":"ref16","author":"baleanu","year":"2011","journal-title":"Fractional Dynamics and Control"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2014.6944707"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.79.031116"},{"key":"ref28","article-title":"UCI machine learning repository","author":"dua","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2009.76"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2015.7172245"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0070"},{"key":"ref6","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.5.1071"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"ref8","article-title":"Reinforcement learning in finite mdps: Pac analysis","volume":"10","author":"strehl","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref1","author":"bertsekas","year":"2019","journal-title":"REINFORCEMENT LEARNING AND OPTIMAL CONTROL"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-03092-0_18"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13520-0_23"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11081-018-9411-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1089\/dia.2008.0138"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/18.119751"},{"key":"ref26","article-title":"Simglucose v0.2.1","author":"xie","year":"2018"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1177\/193229680900300106","article-title":"In silico preclinical trials: a proof of concept in closed-loop control of type 1 diabetes","volume":"3","author":"kovatchev","year":"2009","journal-title":"J Diabetes Sci Technol"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","location":"Austin, TX, USA","start":{"date-parts":[[2021,12,14]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09683076.pdf?arnumber=9683076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T20:24:08Z","timestamp":1654547048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683076\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683076","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}