{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T13:03:43Z","timestamp":1752671023019,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673322","61673326","91746103"],"award-info":[{"award-number":["61673322","61673326","91746103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002663","name":"Northwestern Polytechnical University","doi-asserted-by":"publisher","award":["20720190142"],"award-info":[{"award-number":["20720190142"]}],"id":[{"id":"10.13039\/501100002663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2017J01128","2017J01129"],"award-info":[{"award-number":["2017J01128","2017J01129"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"name":"S\u00ear Cymru II COFUND Fellowship, U.K."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2944912","type":"journal-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T19:44:00Z","timestamp":1569959040000},"page":"144043-144053","source":"Crossref","is-referenced-by-count":8,"title":["A Robotic Writing Framework\u2013Learning Human Aesthetic Preferences via Human\u2013Machine Interactions"],"prefix":"10.1109","volume":"7","author":[{"given":"Xingen","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changle","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6928-2638","authenticated-orcid":false,"given":"Fei","family":"Chao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2115-4909","authenticated-orcid":false,"given":"Longzhi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chih-Min","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changjing","family":"Shang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-017-0410-2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2016.2582526"},{"key":"ref32","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251496"},{"key":"ref36","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","author":"heusel","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2014.2303474"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.08.066"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23878-9_34"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-018-1008-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2647851"},{"key":"ref14","article-title":"Artificial Intelligence-Based Techniques for Emerging Robotics Communication: A Survey and Future Perspectives","author":"alsamhi","year":"2018","journal-title":"arXiv 1804 09671"},{"key":"ref15","first-page":"15","article-title":"Survey of robotic calligraphy research","volume":"11","author":"zeng","year":"2016","journal-title":"CAAI Trans Intell Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.12.013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759586"},{"key":"ref18","first-page":"132","article-title":"Generating calligraphic trajectories with model predictive control","author":"berio","year":"2017","journal-title":"Proc 43rd Graph Interface Conf"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2017.8324509"},{"key":"ref28","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.12.016"},{"key":"ref27","first-page":"1133","article-title":"A Bayesian approach for policy learning from trajectory preference queries","author":"wilson","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2808486"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870758"},{"key":"ref29","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2007.1080"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.06.069"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SMAP.2015.7370086"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/7845102"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2901352"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2015.2468231"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460787"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943186"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.06.010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2018.2882485"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843614500078"},{"key":"ref26","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","author":"christiano","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2016.12.006"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08854069.pdf?arnumber=8854069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T19:39:38Z","timestamp":1628624378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8854069\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2944912","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}