{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:11:14Z","timestamp":1770228674383,"version":"3.49.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0116401"],"award-info":[{"award-number":["2022ZD0116401"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076238"],"award-info":[{"award-number":["62076238"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222606"],"award-info":[{"award-number":["62222606"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902402"],"award-info":[{"award-number":["61902402"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tai.2023.3268612","type":"journal-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T17:24:49Z","timestamp":1682011489000},"page":"751-762","source":"Crossref","is-referenced-by-count":4,"title":["Sample Efficient Reinforcement Learning Using Graph-Based Memory Reconstruction"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0468-9234","authenticated-orcid":false,"given":"Yongxin","family":"Kang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Enmin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Yifan","family":"Zang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2758-7433","authenticated-orcid":false,"given":"Lijuan","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3840-3270","authenticated-orcid":false,"given":"Kai","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Pin","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6801-0510","authenticated-orcid":false,"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref7","volume-title":"Memory, Amnesia, and the Hippocampal System","author":"Eichenbaum","year":"1993"},{"key":"ref8","article-title":"Reconstructive memory for abstract selective recall","volume-title":"Representative Final Project Archive for Stanford CS379C in Spring 2018","author":"Wong","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11571-012-9219-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.102.3.419"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-5371(78)90443-7"},{"issue":"3","key":"ref12","article-title":"Stranger behind the engram: Theories of memory and the psychology of science","volume":"96","author":"Schacter","year":"1984","journal-title":"Amer. J. Psychol."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-018-0318-7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.03.037"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1101\/668483","article-title":"Brain-wide mapping of contextual fear memory engram ensembles supports the dispersed engram complex hypothesis","author":"Roy","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaw4325"},{"key":"ref17","volume-title":"The Organization of Behavior","author":"Hebb","year":"1949"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-018-0031-2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2019.12.025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8279.1933.tb02913.x"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/9780511920219"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0959354313500166"},{"key":"ref23","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schaul","year":"2016"},{"key":"ref24","first-page":"5055","article-title":"Hindsight experience replay","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Andrychowicz","year":"2017"},{"key":"ref25","first-page":"1","article-title":"Model based reinforcement learning for Atari","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kaiser","year":"2019"},{"key":"ref26","first-page":"1","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Ha","year":"2018"},{"key":"ref27","article-title":"Model-free episodic control","author":"Blundell","year":"2016"},{"key":"ref28","first-page":"2827","article-title":"Neural episodic control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pritzel","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/337"},{"key":"ref30","first-page":"1","article-title":"Episodic reinforcement learning with associative memory","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref32","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16981"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/347090.347123"},{"key":"ref35","first-page":"3734","article-title":"Self-attention graph pooling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/361002.361007"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/evco_a_00232"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref41","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref43","first-page":"113","article-title":"Energy-based hindsight experience prioritization","volume-title":"Proc. Conf. Robot Learn.","author":"Zhao","year":"2018"},{"key":"ref44","first-page":"1","article-title":"Exploration via hindsight goal generation","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/365"},{"key":"ref46","first-page":"4380","article-title":"Generalizable episodic memory for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hu","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3085166"},{"key":"ref48","first-page":"1","article-title":"Offline reinforcement learning with value-based episodic memory","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2022.09.029"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/evco.2007.15.3.369"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014602"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10433275\/10105983.pdf?arnumber=10105983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:49Z","timestamp":1755911329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10105983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":51,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tai.2023.3268612","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}