{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:29:22Z","timestamp":1755797362948,"version":"3.44.0"},"reference-count":23,"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\/cog57401.2023.10333131","type":"proceedings-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T13:48:21Z","timestamp":1701697701000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Continuous Episodic Control"],"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":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref7","article-title":"Model-free episodic control","author":"Blundell","year":"2016","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/26216"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4135\/9781446212967.n15"},{"article-title":"Learning from delayed rewards","year":"1989","author":"Watkins","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"volume-title":"Reinforcement learning: An introduction.","year":"2018","author":"Sutton","key":"ref13"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref14"},{"key":"ref15","first-page":"2827","article-title":"Neural episodic control","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Pritzel"},{"article-title":"Continuous control with deep reinforcement learning","volume-title":"4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings","author":"Lillicrap","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/337"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/365"},{"key":"ref19","first-page":"30313","article-title":"Model-based episodic memory induces dynamic hybrid controls","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual","author":"Le"},{"key":"ref20","first-page":"4380","article-title":"Generalizable episodic memory for deep reinforcement learning","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event","volume":"139","author":"Hu"},{"article-title":"Neural map: Structured memory for deep reinforcement learning","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings","author":"Parisotto","key":"ref21"},{"key":"ref22","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018","volume":"80","author":"Haarnoja"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref23"}],"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\/10333131.pdf?arnumber=10333131","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\/10333131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cog57401.2023.10333131","relation":{},"subject":[],"published":{"date-parts":[[2023,8,21]]}}}