{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T10:41:38Z","timestamp":1776076898610,"version":"3.50.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T00:00:00Z","timestamp":1603238400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T00:00:00Z","timestamp":1603238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T00:00:00Z","timestamp":1603238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003626","name":"Defense Acquisition Program Administration","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003626","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,21]]},"DOI":"10.1109\/ictc49870.2020.9289369","type":"proceedings-article","created":{"date-parts":[[2020,12,21]],"date-time":"2020-12-21T22:58:16Z","timestamp":1608591496000},"page":"523-525","source":"Crossref","is-referenced-by-count":8,"title":["Integrate multi-agent simulation environment and multi-agent reinforcement learning (MARL) for real-world scenario"],"prefix":"10.1109","author":[{"given":"Sangho","family":"Yeo","sequence":"first","affiliation":[]},{"given":"Seungjun","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Boreum","family":"Choi","sequence":"additional","affiliation":[]},{"given":"Sangyoon","family":"Oh","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Fully decentralizedmulti-agent reinforcement learning with networked agents","author":"zhang","year":"2018"},{"key":"ref11","first-page":"3235","article-title":"Efficient communication in multiagent reinforcement learning via variance based control","author":"zhang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref13","article-title":"Magent: A many-agent reinforcement learning platform for artificial collective intelligence","author":"zheng","year":"2017"},{"key":"ref14","first-page":"1647","article-title":"The robocup rescue simulation platform","author":"skinner","year":"2010","journal-title":"Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems Volume 1-Volume 1"},{"key":"ref15","article-title":"Fire dynamics simulator with evacuation:Fds+ evac: Technical reference and user’s guide","author":"korhonen","year":"2009"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25808-9_10"},{"key":"ref18","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref19","article-title":"Google research football: A novel reinforcement learning environment","author":"kurach","year":"2019"},{"key":"ref4","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref3","article-title":"Coordinating disaster emergency response with heuristic reinforcement learning","author":"nguyen","year":"2018"},{"key":"ref6","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref5","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref8","article-title":"Learning to communicate to solve riddles with deep distributed recurrent qnetworks","author":"foerster","year":"2016"},{"key":"ref7","article-title":"Deep qlearning from demonstrations","author":"hester","year":"2017"},{"key":"ref2","article-title":"The multi-agent reinforcement learning in malm\\” o (marl\\\" o) competition","author":"perez-liebana","year":"2019"},{"key":"ref1","article-title":"Deep multi-agent reinforcement learning","author":"foerster","year":"2018","journal-title":"Ph D Dissertation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016062"}],"event":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","location":"Jeju, Korea (South)","start":{"date-parts":[[2020,10,21]]},"end":{"date-parts":[[2020,10,23]]}},"container-title":["2020 International Conference on Information and Communication Technology Convergence (ICTC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9289075\/9289076\/09289369.pdf?arnumber=9289369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:19:58Z","timestamp":1656375598000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9289369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,21]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/ictc49870.2020.9289369","relation":{},"subject":[],"published":{"date-parts":[[2020,10,21]]}}}