{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:36Z","timestamp":1740169236816,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["U1811261"],"award-info":[{"award-number":["U1811261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2020.3045300","type":"journal-article","created":{"date-parts":[[2020,12,16]],"date-time":"2020-12-16T21:36:17Z","timestamp":1608154577000},"page":"801-812","source":"Crossref","is-referenced-by-count":0,"title":["Offline Multi-Policy Gradient for Latent Mixture Environments"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4580-4865","authenticated-orcid":false,"given":"Xiaoguang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6228-4908","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1502-4665","authenticated-orcid":false,"given":"Lixin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3171-8889","authenticated-orcid":false,"given":"Ge","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176346060"},{"key":"ref33","article-title":"Emphatic temporal-difference learning","author":"rupam mahmood","year":"2015","journal-title":"arXiv 1507 01569"},{"key":"ref32","first-page":"289","article-title":"Off-policy learning with eligibility traces: A survey","volume":"15","author":"geist","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref31","first-page":"417","article-title":"Off-policy temporal-difference learning with function approximation","author":"precup","year":"2001","journal-title":"Proc ICML"},{"key":"ref30","first-page":"80","article-title":"Eligibility traces for off-policy policy evaluation","volume":"1","author":"precup","year":"2000","journal-title":"Comput Sci Dept Faculty"},{"key":"ref37","first-page":"3014","article-title":"Weighted importance sampling for off-policy learning with linear function approximation","author":"mahmood","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"journal-title":"Probabilistic Graphical Models Principles and Techniques","year":"2009","author":"koller","key":"ref36"},{"key":"ref35","first-page":"1631","article-title":"Generalized emphatic temporal difference learning: Bias-variance analysis","author":"hallak","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref34","first-page":"552","article-title":"Off-policy learning based on weighted importance sampling with linear computational complexity","author":"mahmood","year":"2015","journal-title":"Proc UAI"},{"key":"ref28","first-page":"105","article-title":"Policy-based branch-and-bound for infinite-horizon multi-model Markov decision processes","volume":"1","author":"vinayak ahluwalia","year":"2021","journal-title":"Comput Operations Res"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00186-018-0653-1"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref29"},{"key":"ref2","first-page":"1077","article-title":"Offline policy evaluation across representations with applications to educational games","author":"mandel","year":"2014","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref1","first-page":"737","article-title":"Using reinforcement learning to optimize the policies of an intelligent tutoring system for interpersonal skills training","author":"georgila","year":"2019","journal-title":"Proc 18th Int Conf Auto Agents Multiagent Syst"},{"key":"ref20","article-title":"Selective experience replay for lifelong learning","author":"isele","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793505"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143872"},{"key":"ref23","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","author":"munos","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.14711\/thesis-b655883","article-title":"Reinforcement learning nonstationary environments","author":"choi","year":"2000"},{"article-title":"Distributional reinforcement learning with quantile regression","year":"2017","author":"dabney","key":"ref50"},{"key":"ref51","article-title":"Implicit quantile networks for distributional reinforcement learning","author":"dabney","year":"2018","journal-title":"arXiv 1806 06923"},{"key":"ref55","first-page":"1","article-title":"Learning predictive state representations from non-uniform sampling","author":"grinberg","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942745"},{"key":"ref53","article-title":"Reinforcement learning with policy mixture model for temporal point processes clustering","author":"wu","year":"2019","journal-title":"arXiv 1905 12345"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2018.8468649"},{"key":"ref10","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref11","article-title":"Combining policy gradient and Q-learning","author":"o\u2019donoghue","year":"2016","journal-title":"arXiv 1611 01626"},{"key":"ref40","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","article-title":"Dyna-style planning with linear function approximation and prioritized sweeping","author":"sutton","year":"2012","journal-title":"arXiv 1206 3285"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1416"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1203"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref18","first-page":"1","article-title":"The importance of experience replay database composition in deep reinforcement learning","author":"bruin","year":"2015","journal-title":"Proc NIPS"},{"key":"ref19","article-title":"A deeper look at experience replay","author":"zhang","year":"2017","journal-title":"arXiv 1712 01275"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330754"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3087057"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5220\/0007722000520058"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346981"},{"key":"ref49","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume":"70","author":"bellemare","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref9","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref46","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2018","journal-title":"arXiv 1812 02900"},{"key":"ref45","first-page":"1757","article-title":"Why most decisions are easy in tetris-and perhaps in other sequential decision problems, as well","volume":"48","author":"?im?ek","year":"2016","journal-title":"Mach Learn Res"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330864"},{"key":"ref47","article-title":"Towards end-to-end reinforcement learning of dialogue agents for information access","author":"dhingra","year":"2016","journal-title":"arXiv 1609 00777"},{"key":"ref42","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn (ICML)"},{"key":"ref41","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016","journal-title":"Workshop on Bayesian Deep Learning NIPS"},{"key":"ref44","first-page":"5531","article-title":"Policy gradient using weak derivatives for reinforcement learning","author":"bhatt","year":"2019","journal-title":"Proc IEEE 58th Conf Decision Control (CDC)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430925"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09296301.pdf?arnumber=9296301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:49:59Z","timestamp":1641988199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9296301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3045300","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}