{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T13:46:47Z","timestamp":1762609607417,"version":"build-2065373602"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341899","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"1893-1900","source":"Crossref","is-referenced-by-count":3,"title":["Efficient Q-Learning over Visit Frequency Maps for Multi-Agent Exploration of Unknown Environments"],"prefix":"10.1109","author":[{"given":"Lucas","family":"Chen","sequence":"first","affiliation":[{"name":"Purdue University,Department of Computer Science,West Lafayette,IN,USA,47906"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashvin N.","family":"Iyer","sequence":"additional","affiliation":[{"name":"Purdue University,Department of Computer Science,West Lafayette,IN,USA,47906"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixing","family":"Wang","sequence":"additional","affiliation":[{"name":"Purdue University,Department of Computer Science,West Lafayette,IN,USA,47906"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed H.","family":"Qureshi","sequence":"additional","affiliation":[{"name":"Purdue University,Department of Computer Science,West Lafayette,IN,USA,47906"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759289"},{"key":"ref2","article-title":"Learning to explore using active neural slam","author":"Singh Chaplot","year":"2020","journal-title":"arXiv preprint"},{"volume-title":"PyBullet, a Python module for physics simulation for games, robotics and machine learning","year":"2016-2021","author":"Coumans","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00063"},{"key":"ref5","article-title":"Ex2: Exploration with exemplar models for deep reinforcement learning","volume":"30","author":"Fu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9365-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71541-2_4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019633424543"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/robotics4030365"},{"key":"ref12","article-title":"Exploration in model-based reinforcement learning by empirically estimating learning progress","volume":"25","author":"Lopes","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3115.003.0030"},{"key":"ref14","first-page":"20516","article-title":"Interesting object, curious agent: Learning task-agnostic exploration","volume":"34","author":"Parisi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_24"},{"key":"ref17","article-title":"Episodic curiosity through reachability","author":"Savinov","year":"2018","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"Stadie","year":"2015","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636813"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.035"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130812"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cira.1997.613851"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919868017"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341899.pdf?arnumber=10341899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:46:41Z","timestamp":1762454801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341899\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341899","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}