{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T14:40:16Z","timestamp":1762353616069,"version":"3.32.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801319","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"3470-3475","source":"Crossref","is-referenced-by-count":2,"title":["D-MARL: A Dynamic Communication-Based Action Space Enhancement for Multi Agent Reinforcement Learning Exploration of Large Scale Unknown Environments"],"prefix":"10.1109","author":[{"given":"Gabriele","family":"Calzolari","sequence":"first","affiliation":[{"name":"Luleå University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vidya","family":"Sumathy","sequence":"additional","affiliation":[{"name":"Luleå University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoforos","family":"Kanellakis","sequence":"additional","affiliation":[{"name":"Luleå University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Nikolakopoulos","sequence":"additional","affiliation":[{"name":"Luleå University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Robotic exploration for mapping","year":"2023","author":"Adeleye","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/280765.280773"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCTICT.2016.7514570"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33515-0_49"},{"key":"ref5","first-page":"1","article-title":"Evaluating the efficiency of frontier-based exploration strategies","volume-title":"ISR 2010 (41st International Symposium on Robotics) and ROBOTIK 2010 (6th German Conference on Robotics)","author":"Holz"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2618"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8795787"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844100"},{"key":"ref9","first-page":"11 734","article-title":"Task-agnostic exploration in reinforcement learning","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","article-title":"Meta-reinforcement learning of structured exploration strategies","volume":"31","author":"Gupta","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087426"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034800"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CAC57257.2022.10055585"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146912"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MED54222.2022.9837168"},{"article-title":"Multi-agent reinforcement learning for networked system control","year":"2020","author":"Chu","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5220\/0012384300003636"},{"article-title":"Fully independent communication in multi-agent reinforcement learning","year":"2024","author":"Pina","key":"ref19"},{"volume-title":"Multi-agent reinforcement learning: Foundations and modern approaches","year":"2024","author":"Albrecht","key":"ref20"},{"issue":"1-67","key":"ref21","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","first-page":"15 032","article-title":"Pettingzoo: Gym for multi-agent reinforcement learning","volume":"34","author":"Terry","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Further generalizations of the jaccard index","year":"2021","author":"Costa","key":"ref23"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801319.pdf?arnumber=10801319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:31:49Z","timestamp":1735198309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801319\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801319","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}