{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T12:22:35Z","timestamp":1783426955086,"version":"3.54.6"},"reference-count":457,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1109\/access.2020.3038605","type":"journal-article","created":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T21:44:15Z","timestamp":1605649455000},"page":"209320-209344","source":"Crossref","is-referenced-by-count":220,"title":["A Gentle Introduction to Reinforcement Learning and its Application in Different Fields"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0815-4883","authenticated-orcid":false,"given":"Muddasar","family":"Naeem","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2656-6470","authenticated-orcid":false,"given":"Syed Tahir Hussain","family":"Rizvi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8177-032X","authenticated-orcid":false,"given":"Antonio","family":"Coronato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.744"},{"key":"ref274","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/ICIAICT.2019.8784847"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2988367"},{"key":"ref271","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"arXiv 1705 03122"},{"key":"ref270","first-page":"1","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254746"},{"key":"ref273","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1145\/3077229"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2017.8288203"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254717"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1145\/3132340.3132355"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2018.1700274"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1700246"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2867191"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2018.2865183"},{"key":"ref168","first-page":"1","article-title":"Proactive resource management for LTE in unlicensed spectrum: A deep learning perspective","author":"challita","year":"2017","journal-title":"arXiv 1702 07031"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2809581"},{"key":"ref267","article-title":"Learning to decode for future success","author":"li","year":"2017","journal-title":"arXiv 1701 06549"},{"key":"ref268","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref269","first-page":"1","article-title":"SeqGAN: Sequence generative adversarial nets with policy gradient","author":"yu","year":"2017","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref288","first-page":"1","article-title":"Deep reinforcement learning for simulated autonomous vehicle control","author":"yu","year":"2016"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2823641"},{"key":"ref286","article-title":"Strategy learning for autonomous agents in smart grid markets","author":"reddy","year":"2011","journal-title":"Proc 22nd Int Joint Conf Artif Intell"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2495145"},{"key":"ref181","first-page":"1","article-title":"Cache-enabled wireless networks with opportunistic interference alignment","author":"he","year":"2017","journal-title":"arXiv 1706 09024"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOMW.2014.6849306"},{"key":"ref180","first-page":"1","article-title":"Learning runtime parameters in computer systems with delayed experience injection","author":"schaarschmidt","year":"2016","journal-title":"arXiv 1610 09903"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67540-4_12"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2013.12.013"},{"key":"ref281","first-page":"36","article-title":"Reinforcement learning-based battery energy management in a solar microgrid","volume":"2","author":"mbuwir","year":"2017","journal-title":"Energy-Open"},{"key":"ref185","first-page":"1","article-title":"Echo-liquid state deep learning for 360° content transmission and caching in wireless VR networks with cellular-connected UAVs","author":"chen","year":"2018","journal-title":"arXiv 1804 03284"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2461134"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2018.2805718"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2751641"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7996332"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254503"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2018.2827070"},{"key":"ref187","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.1587\/transcom.2017CQP0014","article-title":"A deep reinforcement learning based approach for cost- and energy-aware multi-flow mobile data offloading","volume":"e101 b","author":"zhang","year":"2018","journal-title":"IEICE Trans Commun"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2018.8362276"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.06.236"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761385"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2396993"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2832219"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9056-7"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTGRID.2010.5622078"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.12.061"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.03.072"},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2924015"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2814606"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2846401"},{"key":"ref153","first-page":"1","article-title":"Artificial neural networks-based machine learning for wireless networks: A tutorial","author":"chen","year":"2017","journal-title":"arXiv 1710 02913"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2836950"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2707140"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389841"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569484"},{"key":"ref151","first-page":"1939","article-title":"Learning to walk in 20 minutes","author":"tedrake","year":"2005","journal-title":"Proc 7th Yale Workshop on Adaptive and Learning Syst"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932842"},{"key":"ref147","first-page":"1607","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"Proc Nat Conf Artif Intell (AAAI)"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2009.V.027"},{"key":"ref149","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s10994-010-5223-6","article-title":"Policy search for motor primitives in robotics","volume":"84","author":"kober","year":"2010","journal-title":"Mach Learn"},{"key":"ref289","article-title":"CARMA: A deep reinforcement learning approach to autonomous driving","author":"vitelli","year":"2016"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422586"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2872440"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2759728"},{"key":"ref164","first-page":"257","article-title":"Deep reinforcement learning for dynamic multichannel access","author":"wang","year":"2017","journal-title":"Proc Int Conf Comput Netw Commun"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647611"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254101"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240545"},{"key":"ref159","first-page":"1","article-title":"Cellular network traffic scheduling with deep reinforcement learning","author":"chinchali","year":"2018","journal-title":"Proc Nat Conf Artif Intell (AAAI)"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2017.2755007"},{"key":"ref158","doi-asserted-by":"crossref","first-page":"1030","DOI":"10.1109\/JSAC.2018.2832820","article-title":"Multiobjective reinforcement learning for cognitive satellite communications using deep neural network ensembles","volume":"36","author":"victor rodrigues ferreira","year":"2018","journal-title":"IEEE J Sel Areas Commun"},{"key":"ref197","first-page":"1","article-title":"UAV-aided cellular communications with deep reinforcement learning against jamming","author":"lu","year":"2019","journal-title":"arXiv 1805 06628"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2815018"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2785414"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952524"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/VTCSpring.2018.8417695"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569635"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2792015"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2018.8690980"},{"key":"ref191","first-page":"1","article-title":"Deep reinforcement learning based computation offloading and resource allocation for MEC","author":"ji","year":"2018","journal-title":"Proc IEEE WCNC"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2878025"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CISP-BMEI.2017.8302157"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1310\/tsr2102-87"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1186\/s12984-015-0048-y"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2737968"},{"key":"ref409","article-title":"Guided deep reinforcement learning for additive manufacturing control application","author":"surana","year":"2016","journal-title":"Deep Reinforcement Learning Workshop NIPS"},{"key":"ref407","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref408","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2517211"},{"key":"ref405","first-page":"1","article-title":"Personalized ad recommendation systems for life-time value optimization with guarantees","author":"theocharous","year":"2015","journal-title":"Proc Int Joint Conf Artif Intell (IJCAI)"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2545523"},{"key":"ref406","article-title":"Recurrent reinforcement learning: A hybrid approach","author":"li","year":"2015","journal-title":"arXiv 1509 03044"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2017.8292280"},{"key":"ref403","first-page":"1406","article-title":"Cumulative prospect theory meets reinforcement learning: Prediction and control","author":"prashanth","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2017.8309082"},{"key":"ref404","first-page":"924","article-title":"Concurrent reinforcement learning from customer interactions","author":"silver","year":"2013","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref202","first-page":"1457","article-title":"Deep Q-learning for self-organizing networks fault management and radio performance improvement","author":"faris","year":"2018","journal-title":"Proc 52nd Asilomar Conf Signals Syst Comput"},{"key":"ref401","doi-asserted-by":"publisher","DOI":"10.1093\/rfs\/hhi019"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.11.015"},{"key":"ref402","doi-asserted-by":"publisher","DOI":"10.3905\/jpm.2004.442611"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00164"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2851783"},{"key":"ref400","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2831240"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1145\/2750858.2807513"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2783439"},{"key":"ref418","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"arXiv 1703 03400"},{"key":"ref419","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref414","article-title":"Explaining how a deep neural network trained with end-to-end learning steers a car","author":"bojarski","year":"2017","journal-title":"arXiv 1704 07911"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2018.8445857"},{"key":"ref415","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019","journal-title":"arXiv 1904 12901"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/WAINA.2017.67"},{"key":"ref416","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2017.2757490"},{"key":"ref417","article-title":"An empirical investigation of the challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2020","journal-title":"arXiv 2003 11881"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.4108\/ICST.SIMUTOOLS2008.3027"},{"key":"ref410","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280935"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422706"},{"key":"ref411","first-page":"2130","article-title":"Differentially private policy evaluation","author":"balle","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref217","first-page":"1","article-title":"Cellular-connected UAVs over 5G: Deep reinforcement learning for interference management","author":"challita","year":"2018","journal-title":"arXiv 1801 05500"},{"key":"ref412","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140444"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref413","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"arXiv 1604 07316 [cs]"},{"key":"ref219","first-page":"1","article-title":"A deep-reinforcement learning approach for software-defined networking routing optimization","author":"stampa","year":"2017","journal-title":"arXiv 1709 07080"},{"key":"ref420","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12331-3"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1153"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1145\/1096536.1096551"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1062"},{"key":"ref228","article-title":"Neural models for information retrieval","author":"mitra","year":"2017","journal-title":"arXiv 1705 01509"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1061"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1060"},{"key":"ref225","article-title":"Learning to generate reviews and discovering sentiment","author":"radford","year":"2017","journal-title":"arXiv 1704 01444"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1261"},{"key":"ref223","first-page":"1051","article-title":"From language to programs: Bridging reinforcement learning and maximum marginal likelihood","author":"guu","year":"2015","journal-title":"Proceedings of the 27th Annual Meeting of the Association for Computational Linguistics (ACL)"},{"key":"ref127","first-page":"1","article-title":"Reinforcement learning of hierarchical skills on the Sony Aibo robot","author":"soni","year":"2006","journal-title":"Proc Int Conf Develop Learn"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9120-4"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/RAAD.2010.5524570"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2009.5379568"},{"key":"ref129","first-page":"465","article-title":"A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref128","first-page":"944","article-title":"Automatic gait optimization with Gaussian process regression","author":"lizotte","year":"2007","journal-title":"Proc Int Joint Conf Artif Intell (IJCAI)"},{"key":"ref130","article-title":"Learning to control a low-cost manipulator using data-efficient reinforcement learning","author":"deisenroth","year":"2007","journal-title":"Robotics Science and Systems"},{"key":"ref133","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref134","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017","journal-title":"arXiv 1707 02286"},{"key":"ref131","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref132","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref232","article-title":"Grounded language learning in a simulated 3D world","author":"hermann","year":"2017","journal-title":"arXiv 1706 06551"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00004"},{"key":"ref230","article-title":"A deep reinforced model for abstractive summarization","author":"paulus","year":"2017","journal-title":"arXiv 1705 04304"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1003"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1179"},{"key":"ref238","article-title":"Assessing bert’s syntactic abilities. Conference on robtics research","author":"goldberg","year":"2019","journal-title":"CoRR"},{"key":"ref235","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref237","first-page":"2121","article-title":"A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc NIPS"},{"key":"ref236","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref138","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"kolve","year":"2017","journal-title":"arXiv 1712 05474"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref139","first-page":"1312","article-title":"Universal value function approximators","author":"schaul","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref141","article-title":"Memory augmented control networks","author":"khan","year":"2017","journal-title":"arXiv 1709 05706"},{"key":"ref142","article-title":"One-shot reinforcement learning for robot navigation with interactive replay","author":"bruce","year":"2017","journal-title":"arXiv 1711 10137"},{"key":"ref143","article-title":"Active neural localization","author":"chaplot","year":"2018","journal-title":"arXiv 1801 08214"},{"key":"ref144","article-title":"Semi-parametric topological memory for navigation","author":"savinov","year":"2018","journal-title":"arXiv 1803 00653"},{"key":"ref2","volume":"2","author":"sutton","year":"2015","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9132-0"},{"key":"ref1","author":"mitchell","year":"1997","journal-title":"Machine Learning"},{"key":"ref241","article-title":"What do you learn from context? Probing for sentence structure in contextualized word representations","author":"tenney","year":"2019","journal-title":"Proc ICLR"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/880"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/331"},{"key":"ref244","article-title":"Learning to understand goal specifications by modelling reward","author":"bahdanau","year":"2019","journal-title":"Proc ICLR"},{"key":"ref240","first-page":"935","article-title":"Zero-shot learning through cross-modal transfer","author":"socher","year":"2013","journal-title":"Proc NIPS"},{"key":"ref248","first-page":"10025","article-title":"Hierarchical decision making by generating and following natural language instructions","author":"hu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref247","first-page":"166","article-title":"Modular multitask reinforcement learning with policy sketches","author":"andreas","year":"2017","journal-title":"Proc ICML"},{"key":"ref246","first-page":"53","article-title":"Neural modular control for embodied question answering","author":"das","year":"2018","journal-title":"Proc of CoRL"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref249","first-page":"2659","article-title":"An extensive, lightweight and flexible research platform for real-time strategy games","author":"tian","year":"2017","journal-title":"Proc NIPS"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/SNAMS.2019.8931857"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3378184.3378223"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30143-9_2"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2882245"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-012-0409-8"},{"key":"ref104","first-page":"26","article-title":"A reinforcement learning-based approach for the risk management of e-Health environments: A case study","author":"paragliola","year":"2018","journal-title":"Proc 14th Int Conf Signal-Image Technol Internet-Based Syst (SITIS)"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/s40860-019-00084-z"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3023553"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1163\/156855307782148550"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.3390\/robotics2030122"},{"key":"ref250","first-page":"1","article-title":"Hierarchical and interpretable skill acquisition in multi-task reinforcement learning","author":"shu","year":"2018","journal-title":"Proc ICLR"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3484"},{"key":"ref254","first-page":"4","article-title":"Walk the talk: Connecting language, knowledge, and action in route instructions","author":"macmahon","year":"2006","journal-title":"Proc AAAI"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1145\/1734454.1734553"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.3115\/1699571.1699637"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11263"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00209"},{"key":"ref256","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11832","article-title":"Gated attention architectures for task-oriented language grounding","author":"chaplot","year":"2018","journal-title":"Proc AAAI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007944"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1106"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1820238116"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref12","article-title":"Combining model-based and model-free updates for trajectory-centric reinforcement learning","author":"chebotar","year":"2017","journal-title":"arXiv 1703 03078 [cs]"},{"key":"ref13","article-title":"Probability and random processes","volume":"2","author":"grimmett","year":"1992"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref15","author":"barto","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570760"},{"key":"ref16","author":"rummery","year":"1994","journal-title":"On-line Q-learning using connectionist systems"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1642157"},{"key":"ref17","article-title":"Learning from delayed rewards","volume":"3","author":"watkins","year":"1989"},{"key":"ref18","article-title":"Convergence of Q-learning: A simple proof","author":"melo","year":"0"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(97)00042-0"},{"key":"ref19","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref116","article-title":"A real-time model-based reinforcement learning architecture for robot control","author":"hester","year":"2011","journal-title":"CoRR"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.004"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5650243"},{"key":"ref122","first-page":"1","article-title":"Learning motion skills from expert demonstrations and own experience using Gaussian process regression","author":"gr\u00e4ve","year":"2010","journal-title":"Proc ISRAM"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354345"},{"key":"ref260","article-title":"Interpreting visually-grounded navigation instructions in real environments","author":"anderson","year":"2018","journal-title":"Proc CVPR"},{"key":"ref261","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v25i1.7974","article-title":"Learning to interpret natural language navigation instructions from observations","author":"chen","year":"2011","journal-title":"Proc AAAI"},{"key":"ref262","article-title":"Understanding natural language commands for robotic navigation and mobile manipulation","author":"tellex","year":"0"},{"key":"ref263","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"Proc AAAI"},{"key":"ref264","article-title":"Learning to generalize from sparse and underspecified rewards","author":"agarwal","year":"2019","journal-title":"arXiv 1902 07198"},{"key":"ref265","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Proc NIPS"},{"key":"ref266","first-page":"1","article-title":"Apprenticeship learning about multiple intentions","author":"babes","year":"2011","journal-title":"Proc ICML"},{"key":"ref365","article-title":"DeepMind lab","author":"beattie","year":"2016","journal-title":"arXiv 1612 03801"},{"key":"ref364","article-title":"TorchCraft: A library for machine learning research on real-time strategy games","author":"synnaeve","year":"2016","journal-title":"arXiv 1611 00625"},{"key":"ref363","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"arXiv 1708 04782"},{"key":"ref362","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref361","article-title":"OpenSpiel: A framework for reinforcement learning in games","author":"lanctot","year":"2019","journal-title":"arXiv 1908 09453"},{"key":"ref360","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490422"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asu043"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2014.07.004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1111\/j.1541-0420.2011.01572.x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/sim.3720"},{"key":"ref359","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"ref30","author":"humphrey","year":"2017","journal-title":"Using Reinforcement Learning to Personalize Dosing Strategies in a Simulated Cancer Trial With High Dimensional Data"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/s10994-010-5229-0","article-title":"Informing sequential clinical decision-making through reinforcement learning: An empirical study","volume":"84","author":"shortreed","year":"2010","journal-title":"Mach Learn"},{"key":"ref357","article-title":"Unity: A general platform for intelligent agentst","author":"arthur","year":"2018","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1080\/0952813X.2017.1292319"},{"key":"ref358","first-page":"4246","article-title":"The Malmo platform for artificial intelligence experimentation","author":"matthew","year":"2016","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2016.06.119"},{"key":"ref355","first-page":"1","article-title":"Action permissibility in deep reinforcement learning and application to autonomous driving","author":"sahisnu","year":"2018","journal-title":"Proc ACM SIGKDD Conf Knowl Discovery Data Mining"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI.2017.45"},{"key":"ref356","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1613\/jair.3912","article-title":"The arcade learning environment: An evaluation platform for general agents","volume":"47","author":"marc","year":"2013","journal-title":"J Artif Intell Res"},{"key":"ref352","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490423"},{"key":"ref351","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST.2018.8426160"},{"key":"ref354","article-title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","author":"jaderberg","year":"2018","journal-title":"CoRR"},{"key":"ref353","first-page":"1553","article-title":"A deep hierarchical approach to lifelong learning in minecraft","author":"chen","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref350","article-title":"Dota 2 with large scale deep reinforcement learning","author":"christopher","year":"2019","journal-title":"arXiv 1912 06680"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S1359-6446(05)03490-2"},{"key":"ref27","first-page":"1671","article-title":"Adaptive treatment of epilepsy via batch-mode reinforcement learning","author":"guez","year":"2008","journal-title":"Proc AAAI"},{"key":"ref29","year":"2004","journal-title":"Challenge and Opportunity on the Critical Path to New Medical Products"},{"key":"ref20","article-title":"A developmental model of trust in humanoid robot","author":"massimiliano","year":"2018"},{"key":"ref348","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2018.07.015"},{"key":"ref349","first-page":"2930","article-title":"Playing hard exploration games by watching YouTube","author":"aytar","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","article-title":"A Bayesian framework for reinforcement learning","author":"strens","year":"2000"},{"key":"ref21","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","author":"welling","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref344","article-title":"A survey of deep reinforcement learning in video games","author":"shao","year":"2019","journal-title":"arXiv 1912 10944"},{"key":"ref23","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref345","first-page":"75","article-title":"High-level reinforcement learning in strategy games","volume":"1","author":"amato","year":"2010","journal-title":"Proc 9th Int Conf Auton Agents Multiagent Syst (AAMAS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101964"},{"key":"ref346","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref25","article-title":"Deep recurrent Q-Learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"arXiv 1507 06527"},{"key":"ref347","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2012.6214281"},{"key":"ref50","first-page":"511","article-title":"A reinforcement learning framework for medical image segmentation","author":"sahba","year":"2006","journal-title":"Proc IEEE Int Joint Conf Neural Netw"},{"key":"ref383","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2828859"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5772\/5291"},{"key":"ref382","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc 12th Int Conf Neural Inf Process Syst"},{"key":"ref381","first-page":"1","article-title":"Modified leakage based user scheduling for MU-MIMO systems","author":"naeem","year":"2015","journal-title":"Proc IEEE 13th Int Conf Frontiers Inf Technol (FIT)"},{"key":"ref380","doi-asserted-by":"publisher","DOI":"10.1109\/ICICT.2015.7469587"},{"key":"ref387","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref386","first-page":"1","article-title":"Deep reinforcement learning in large discrete action spaces","author":"arnold","year":"2016","journal-title":"arXiv 1512 07679"},{"key":"ref385","doi-asserted-by":"publisher","DOI":"10.14778\/3199517.3199521"},{"key":"ref384","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref59","first-page":"895","article-title":"Learning to diagnose: Assimilating clinical narratives using deep reinforcement learning","author":"ling","year":"2017","journal-title":"Proc 8th Int Joint Conf Natural Lang Process"},{"key":"ref379","article-title":"Performance analysis of scheduling algorithms for multiuser MIMO systems","author":"naeem","year":"2016","journal-title":"Proc IEEE 12th Int Conf Appl Sci Technol"},{"key":"ref58","article-title":"A reinforcement learning approach to obtain treatment strategies in sequential medical decision problems","author":"poolla","year":"2003"},{"key":"ref57","first-page":"271","article-title":"Diagnostic inferencing via improving clinical concept extraction with deep reinforcement learning: A preliminary study","volume":"68","author":"ling","year":"2017","journal-title":"Proc Mach Learn Healthcare Conf"},{"key":"ref377","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.123"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5772\/5292"},{"key":"ref378","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-019-06222-3"},{"key":"ref55","author":"mcpherson","year":"2017","journal-title":"Clinical Diagnosis and Management by Laboratory Methods"},{"key":"ref54","author":"kluckner","year":"2018","journal-title":"Medical Scanner Teaches Itself to Optimize Clinical Protocols and Image Acquisition"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_76"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2342-8-8"},{"key":"ref370","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","author":"boyan","year":"1993","journal-title":"Proc 6th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref372","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997286"},{"key":"ref40","article-title":"A reinforcement learning system to encourage physical activity in diabetes patients","author":"hochberg","year":"2016","journal-title":"CoRR"},{"key":"ref371","first-page":"45","article-title":"A distributed reinforcement learning scheme for network routing","author":"littman","year":"1993","journal-title":"Proc Int Workshop Appl Neural Networks Telecommun 2"},{"key":"ref374","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2881964"},{"key":"ref373","doi-asserted-by":"publisher","DOI":"10.1109\/CCAAW.2017.8001607"},{"key":"ref376","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2812733"},{"key":"ref375","first-page":"1","article-title":"Deep reinforcement learning for distributed dynamic power allocation in wireless networks","author":"nasir","year":"2019","journal-title":"arXiv 1808 00490"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6675-8_674"},{"key":"ref5","volume":"2","author":"russell","year":"2003","journal-title":"Artificial Intelligence A Modern Approach"},{"key":"ref8","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CCECE.2003.1226121"},{"key":"ref7","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0007362"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0253-x"},{"key":"ref366","first-page":"4246","article-title":"The malmo platform for artificial intelligence experimentation","author":"johnson","year":"2016","journal-title":"Proc IJCAI"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"key":"ref367","first-page":"1114","article-title":"A reinforcement learning approach to job-shop scheduling","volume":"2","author":"zhang","year":"1995","journal-title":"Proc 14th Int Joint Conf Artif Intell (IJCAI)"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/34.659932"},{"key":"ref368","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref47","article-title":"Continuous state-space models for optimal sepsis treatment—A deep reinforcement learning approach","author":"raghu","year":"2017","journal-title":"CoRR"},{"key":"ref369","first-page":"886","article-title":"Online resource allocation using decompositional reinforcement learning","author":"tesauro","year":"2005","journal-title":"Proc AAAI"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2012.06.002"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1303386"},{"key":"ref44","article-title":"Representation and reinforcement learning for personalized glycemic control in septic patients","author":"weng","year":"2017","journal-title":"CoRR"},{"key":"ref43","article-title":"Optimising the management of severe infections in intensive care with reinforcement learning","author":"anthony","year":"2016","journal-title":"J Exp Theor Artif Intell"},{"key":"ref320","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967908"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.01.007"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2010.10.003"},{"key":"ref72","author":"kim","year":"2014","journal-title":"Inverse Reinforcement Learning for Micro-Turn Management"},{"key":"ref71","author":"daniel","year":"2014","journal-title":"Speech and Language Processing An Introduction to Natural Language Processing Computational Linguistics and Speech Recognition"},{"key":"ref70","article-title":"Deep reinforcement learning for sepsis treatment","author":"raghu","year":"2017","journal-title":"CoRR"},{"key":"ref76","first-page":"120","article-title":"Predicting the micro-timing of user input for an incremental spoken dialogue system that completes a user’s ongoing turn","author":"baumann","year":"2011"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1109\/CAC.2017.8244061"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-013-0147-7"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.23919\/SICE.2017.8105597"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.5087\/dad.2011.107"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2919736"},{"key":"ref75","first-page":"1","article-title":"Detecting the status of a predictive incremental speech understanding model for real time decision making in a spoken dialogue system","author":"david","year":"2011","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2019.2902661"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890685"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-1903"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2018.10.003"},{"key":"ref79","first-page":"1706","article-title":"Reinforcement learning of cooperative persuasive dialogue policies using framing","author":"hiraoka","year":"2014","journal-title":"Proc 25th Int Conf Comput Linguistics"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2019.8756797"},{"key":"ref457","first-page":"1","article-title":"Learning to perform physics experiments via deep reinforcement learning","author":"denil","year":"2017","journal-title":"Proc ICLR"},{"key":"ref456","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref455","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_14"},{"key":"ref454","article-title":"Deep reinforcement learning for clinical decision support: A brief survey","author":"liu","year":"2019","journal-title":"arXiv 1907 09475v1"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2018.00038"},{"key":"ref450","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref451","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00251"},{"key":"ref452","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume":"70","author":"haarnoja","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref453","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.67.026706"},{"key":"ref310","article-title":"Deep reinforcement learning for wireless sensor scheduling in cyber-physical systems","author":"leong","year":"2018","journal-title":"arXiv 1809 05149"},{"key":"ref60","first-page":"161","article-title":"Reinforcement learning with action-derived rewards for chenotheropy and clinical trial using dosing regimen selection","author":"yauney","year":"2018","journal-title":"Proc Mach Learn Healthcare Conf"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6939-14-55"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.329.7456.15"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/SECON.2015.7133041"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2894437"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.07.182"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05816-6_3"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7591355"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2514358"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.2247"},{"key":"ref306","article-title":"Vehicular edge computing via deep reinforcement learning","author":"qi","year":"2018","journal-title":"arXiv 1901 04290"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.mbs.2017.08.004"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2882583"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12625"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2906789"},{"key":"ref69","article-title":"Precision medicine as a control problem: Using simulation and deep reinforcement learning to discover adaptive, personalized multi-cytokine therapy for sepsis","author":"petersen","year":"2018","journal-title":"CoRR"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317735"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2878435"},{"key":"ref444","article-title":"Data augmentation generative adversarial networks","author":"antoniou","year":"2017","journal-title":"arXiv 1711 04340"},{"key":"ref443","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101552"},{"key":"ref446","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1987.10478458"},{"key":"ref445","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2019.01.001"},{"key":"ref448","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2925719"},{"key":"ref447","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref308","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2949997"},{"key":"ref449","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2019.107377"},{"key":"ref441","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00132"},{"key":"ref442","article-title":"Experienced deep reinforcement learning with generative adversarial networks (GANs) for model-free ultra reliable low latency communication","author":"kasgari","year":"2019","journal-title":"arXiv 1911 03264"},{"key":"ref440","first-page":"1582","article-title":"Addressing environment non-stationarity by repeating Q-learning updates","volume":"17","author":"abdallah","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1089\/cpb.2005.8.187"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1586\/17434440.2013.827515"},{"key":"ref93","article-title":"A reinforcement learning approach to weaning of mechanical ventilation in intensive care units","author":"prasad","year":"2017","journal-title":"CoRR"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s10729-014-9304-0"},{"key":"ref91","first-page":"852","article-title":"Autonomic learning through stochastic games for rational allocation of scarce medical resources","author":"kamal","year":"2013","journal-title":"Proc IFIP\/IEEE Int Symp Integr Netw Manage"},{"key":"ref342","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.399"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0060883"},{"key":"ref343","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC.2019.8666545"},{"key":"ref340","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.43"},{"key":"ref341","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.148"},{"key":"ref336","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.424"},{"key":"ref335","first-page":"127","article-title":"Tree-structured reinforcement learning for sequential object localization","author":"jie","year":"2016","journal-title":"Proc Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref334","article-title":"A connection between gans, inverse reinforcement learning, and energy-based models","author":"finn","year":"0","journal-title":"Proc Workshop Adversarial Training (NIPS)"},{"key":"ref333","article-title":"Connecting generative adversarial networks and actor-critic methods","author":"pfau","year":"2016","journal-title":"arXiv 1610 01945"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1097\/HTR.0000000000000203"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6947-7-41"},{"key":"ref339","first-page":"5173","article-title":"Saliency-based sequential image attention with multiset prediction","author":"welleck","year":"2017","journal-title":"Proc Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.jns.2013.07.2004"},{"key":"ref338","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.316"},{"key":"ref97","author":"sohlberg","year":"2017","journal-title":"Cognitive Rehabilitation An Integrative Neuropsychological Approach"},{"key":"ref337","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.748"},{"key":"ref439","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143872"},{"key":"ref438","article-title":"Reinforcement learning based control of traffic lights in non-stationary environments: A case study in a microscopic simulator","author":"de oliveira","year":"2006","journal-title":"EuMA Proc"},{"key":"ref437","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZ-IEEE.2014.6891757"},{"key":"ref436","article-title":"Reinforcement learning in non-stationary environments","author":"padakandla","year":"2019","journal-title":"arXiv 1905 03970"},{"key":"ref435","first-page":"345","article-title":"Reinforcement learning algorithm for partially observable Markov decision problems","author":"jaakkola","year":"1995","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref434","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47766-4_6"},{"key":"ref433","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref432","first-page":"2125","article-title":"Variational information maximisation for intrinsically motivated reinforcement learning","author":"mohamed","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref430","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814879"},{"key":"ref431","article-title":"Rethinking bias-variance trade-off for generalization of neural networks","author":"yang","year":"2020","journal-title":"arXiv 2002 11328"},{"key":"ref82","first-page":"512","article-title":"Active advice seeking for inverse reinforcement learning","author":"odom","year":"2016","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2015.7392941"},{"key":"ref84","author":"hamidreza","year":"2016","journal-title":"Building Dialogue POMDPs from Expert Dialogue An End-to-End Approach"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2013.79"},{"key":"ref330","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.180"},{"key":"ref80","doi-asserted-by":"crossref","DOI":"10.1007\/978-4-431-53936-0","author":"yamagishi","year":"2011","journal-title":"Trust The Evolutinary Game of Mind and Society"},{"key":"ref331","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref332","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.605"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/BioRob.2012.6290309"},{"key":"ref323","doi-asserted-by":"publisher","DOI":"10.3390\/en12122291"},{"key":"ref322","article-title":"Deep reinforcement learning solutions for energy microgrids management","author":"francois-lavet","year":"2016","journal-title":"Proceedings of the 8th European Workshop on Reinforcement Learning (EWRL)"},{"key":"ref325","article-title":"Reinforcement learning-based energy trading for microgrids","author":"xiao","year":"2018","journal-title":"arXiv 1801 06285"},{"key":"ref324","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2834219"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2017.2700395"},{"key":"ref327","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00717"},{"key":"ref429","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.08.354"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2960636"},{"key":"ref87","article-title":"Reinforcement learning in models of adaptive medical treatment strategies","author":"vincenti","year":"2014"},{"key":"ref329","article-title":"Teaching a machine to read maps with deep reinforcement learning","author":"brunner","year":"2018","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2009.090517"},{"key":"ref328","article-title":"Image classification by reinforcement learning with two-state Q-learning","author":"hafiz","year":"2020","journal-title":"arXiv 2007 01298"},{"key":"ref426","doi-asserted-by":"publisher","DOI":"10.1145\/2347736.2347755"},{"key":"ref425","doi-asserted-by":"publisher","DOI":"10.3390\/sym12101685"},{"key":"ref428","article-title":"Merging deterministic policy gradient estimations with varied bias-variance tradeoff for effective deep reinforcement learning","author":"chen","year":"2019","journal-title":"arXiv 1911 10527"},{"key":"ref427","first-page":"3846","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","author":"gu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref422","article-title":"Safe exploration in continuous action spaces","author":"dalal","year":"2018","journal-title":"arXiv 1801 08757"},{"key":"ref421","article-title":"Deep reinforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2016","journal-title":"arXiv 1512 07679"},{"key":"ref424","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.01.002"},{"key":"ref423","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref399","author":"hull","year":"2014","journal-title":"Options Futures and Other Derivatives"},{"key":"ref389","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.748"},{"key":"ref388","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.286"},{"key":"ref390","first-page":"1","article-title":"Deep reinforcement learning for visual object tracking in videos","author":"zhang","year":"2017","journal-title":"arXiv 1701 08893"},{"key":"ref397","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbankfin.2010.06.001"},{"key":"ref398","article-title":"A comprehensive survey of data mining-based fraud detection research","author":"phua","year":"2010","journal-title":"arXiv 1009 6119"},{"key":"ref395","first-page":"161","article-title":"Trading off scientific knowledge and user learning with multi-armed bandits","author":"liu","year":"2014","journal-title":"Educational Data Mining (EDM)"},{"key":"ref396","first-page":"1077","article-title":"Offline policy evaluation across representations with applications to educational games","author":"mandel","year":"2014","journal-title":"Proc Int'l Joint Conf Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref393","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref394","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487379"},{"key":"ref391","first-page":"4","article-title":"Feature selection based on reinforcement learning for objectrecognition","author":"pinol","year":"2012","journal-title":"Adaptive and Learning Agents Workshop"},{"key":"ref392","first-page":"1","article-title":"Reinforcement learning of visual descriptors for object recognition","author":"pinol","year":"2014"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09261348.pdf?arnumber=9261348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T14:59:07Z","timestamp":1697122747000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9261348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":457,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3038605","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}