{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T10:03:56Z","timestamp":1766484236248,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811965","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"6232-6239","source":"Crossref","is-referenced-by-count":5,"title":["A Deep Reinforcement Learning Environment for Particle Robot Navigation and Object Manipulation"],"prefix":"10.1109","author":[{"given":"Jeremy","family":"Shen","sequence":"first","affiliation":[{"name":"Stuyvesant High School,New York,NY,USA,10280"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erdong","family":"Xiao","sequence":"additional","affiliation":[{"name":"New York University,Brooklyn,NY,USA,11201"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Liu","sequence":"additional","affiliation":[{"name":"New York University,Brooklyn,NY,USA,11201"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Feng","sequence":"additional","affiliation":[{"name":"New York University,Brooklyn,NY,USA,11201"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Distributed localization without direct communication inspired by statistical mechanics","author":"wang","year":"2020","journal-title":"ArXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967985"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2946724"},{"key":"ref13","article-title":"Fully distributed multi-robot collision avoidance via deep reinforcement learning for safe and efficient navigation in complex scenarios","author":"fan","year":"2018","journal-title":"ArXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref15","article-title":"Using reinforcement learning for real-time trajectory planning of aerial multi agent systems","author":"kumar","year":"2019","journal-title":"TJHSST Computer Systems Research Lab Senior Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00040"},{"key":"ref17","article-title":"Distributed reinforcement learning for cooperative multi-robot object manipulation","author":"ding","year":"2020","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3016951"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3076530"},{"journal-title":"Stable baselines3","year":"2019","author":"raffin","key":"ref28"},{"key":"ref4","article-title":"Asyn-chronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ArXiv"},{"journal-title":"Google research football","year":"2019","key":"ref27"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aax4316"},{"key":"ref5","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.188002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/science.abc6182"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1022-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abd0272"},{"key":"ref1","article-title":"Particle robots a new species of hybrid bio-inspired robotics","author":"mateos","year":"2020","journal-title":"ArXiv"},{"journal-title":"Multi-Agent-Reinforcement-Learning-Environment","year":"2018","author":"jiang","key":"ref20"},{"key":"ref22","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2020","journal-title":"ArXiv"},{"key":"ref21","article-title":"Magent: A many-agent reinforcement learning platform for artificial collective intelligence","author":"zheng","year":"2017","journal-title":"ArXiv"},{"journal-title":"Playground","year":"2019","key":"ref24"},{"key":"ref23","article-title":"Emergent tool use from multi-agent autocurricula","author":"baker","year":"2020","journal-title":"ArXiv"},{"journal-title":"StarCraft II","year":"2019","author":"samvelyan","key":"ref26"},{"journal-title":"Neural mmos","year":"2019","author":"suarez","key":"ref25"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2022,5,23]]},"location":"Philadelphia, PA, USA","end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811965.pdf?arnumber=9811965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T17:44:27Z","timestamp":1717609467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811965","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}