{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:31:16Z","timestamp":1755797476750,"version":"3.44.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"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":[[2023,8,21]]},"DOI":"10.1109\/cog57401.2023.10333174","type":"proceedings-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T13:48:21Z","timestamp":1701697701000},"page":"1-9","source":"Crossref","is-referenced-by-count":3,"title":["Two-Memory Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zhao","family":"Yang","sequence":"first","affiliation":[{"name":"Leiden Institute of Advanced Computer Science Leiden University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas. M.","family":"Moerland","sequence":"additional","affiliation":[{"name":"Leiden Institute of Advanced Computer Science Leiden University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mike","family":"Preuss","sequence":"additional","affiliation":[{"name":"Leiden Institute of Advanced Computer Science Leiden University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aske","family":"Plaat","sequence":"additional","affiliation":[{"name":"Leiden Institute of Advanced Computer Science Leiden University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04301-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05172-4"},{"article-title":"Model-free episodic control","year":"2016","author":"Blundell","key":"ref6"},{"key":"ref7","first-page":"2827","article-title":"Neural episodic control","volume-title":"International Conference on Machine Learning","author":"Pritzel"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/337"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/365"},{"article-title":"Generalizable episodic memory for deep reinforcement learning","year":"2021","author":"Hu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref12","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S0028-3932(02)00157-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0409070102"},{"volume-title":"Reinforcement learning: An introduction.","year":"2018","author":"Sutton","key":"ref15"},{"article-title":"Continuous episodic control","year":"2022","author":"Yang","key":"ref16"},{"key":"ref17","article-title":"Sample-efficient deep reinforcement learning via episodic backward update","volume":"32","author":"Lee","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Prioritized experience replay","year":"2015","author":"Schaul","key":"ref18"},{"key":"ref19","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Curriculum-guided hindsight experience replay","volume":"32","author":"Fang","year":"2019","journal-title":"Advances in neural information processing systems"},{"article-title":"Event tables for efficient experience replay","year":"2022","author":"Kompella","key":"ref21"},{"article-title":"Minatar: An atari-inspired testbed for thorough and reproducible reinforcement learning experiments","year":"2019","author":"Young","key":"ref22"}],"event":{"name":"2023 IEEE Conference on Games (CoG)","start":{"date-parts":[[2023,8,21]]},"location":"Boston, MA, USA","end":{"date-parts":[[2023,8,24]]}},"container-title":["2023 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10333091\/10333129\/10333174.pdf?arnumber=10333174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:29:41Z","timestamp":1755545381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10333174\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/cog57401.2023.10333174","relation":{},"subject":[],"published":{"date-parts":[[2023,8,21]]}}}