{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T18:42:41Z","timestamp":1730227361822,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T00:00:00Z","timestamp":1693353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T00:00:00Z","timestamp":1693353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,30]]},"DOI":"10.1109\/icac57885.2023.10275190","type":"proceedings-article","created":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T17:58:56Z","timestamp":1697479136000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Joint Recurrent Actor-Critic Model for Partially Observable Control"],"prefix":"10.1109","author":[{"given":"Han","family":"Xu","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Liang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref5","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Memory-based control with recurrent neural networks","author":"Heess","year":"2015","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50031-9"},{"key":"ref8","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","author":"Lee","year":"2019","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref10","first-page":"2450","article-title":"Recurrent world models facilitate policy evolution","author":"Ha","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"Variational recurrent models for solving partially observable control tasks","author":"Han","year":"2019","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"90","volume-title":"Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments","author":"Schmidhuber","year":"1990"},{"key":"ref13","first-page":"500","article-title":"learning in markovian and nonmarkovian environments","author":"Reinforcement","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"Deep variational reinforcement learning for pomdps","author":"Igl","year":"2018","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref16","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","volume-title":"International Conference on Machine Learning","author":"Pascanu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref18","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"article-title":"Deep recurrent q-learning for partially observable mdps","volume-title":"2015 AAAI Fall Symposium Series","author":"Hausknecht","key":"ref21"},{"article-title":"Recurrent experience replay in distributed reinforcement learning","volume-title":"7th International Conference on Learning Representations","author":"Kapturowski","key":"ref22"},{"volume-title":"Learning From Delayed Rewards","year":"1989","author":"Watkins","key":"ref23"},{"article-title":"Issues in using function approximation for reinforcement learning","volume-title":"Proceedings of the 1993 Connectionist Models Summer School Hillsdale","author":"Thrun","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022633531479"},{"volume-title":"Estimator variance in reinforcement learning: Theoretical problems and practical solutions","year":"1997","author":"Pendrith","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1060.0614"},{"key":"ref28","first-page":"2613","article-title":"Double q-learning","author":"Van Hasselt","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref30","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Fujimoto"},{"key":"ref31","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"}],"event":{"name":"2023 28th International Conference on Automation and Computing (ICAC)","start":{"date-parts":[[2023,8,30]]},"location":"Birmingham, United Kingdom","end":{"date-parts":[[2023,9,1]]}},"container-title":["2023 28th International Conference on Automation and Computing (ICAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10275139\/10275143\/10275190.pdf?arnumber=10275190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T06:32:28Z","timestamp":1712903548000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10275190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icac57885.2023.10275190","relation":{},"subject":[],"published":{"date-parts":[[2023,8,30]]}}}