{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:35:27Z","timestamp":1781109327671,"version":"3.54.1"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/robio.2018.8664803","type":"proceedings-article","created":{"date-parts":[[2019,3,19]],"date-time":"2019-03-19T00:01:56Z","timestamp":1552953716000},"page":"237-242","source":"Crossref","is-referenced-by-count":27,"title":["Hierarchical Reinforcement Learning Framework Towards Multi-Agent Navigation"],"prefix":"10.1109","author":[{"given":"Wenhao","family":"Ding","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuaijun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huihuan","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongquan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"Computer Science"},{"key":"ref11","article-title":"Deter-ministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref12","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref13","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref15","article-title":"Smooth and collision-free navigation for multiple robots under differential-drive constraints","author":"chen","year":"2017","journal-title":"International Conference on Robotics and Automation (ICRA)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460968"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-13-2122-1","article-title":"Understanding human behavior in crowds by imitating the decision-making process","author":"zou","year":"2018","journal-title":"The AAAI Conference of Artificial Intelligence (AAAI)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1109\/TRO.2011.2120810","article-title":"The hybrid reciprocal velocity obstacle","volume":"4","author":"snape","year":"2011","journal-title":"IEEE Transactions on Robotics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref3","first-page":"3","article-title":"Reciprocal n-body collision avoidance","volume":"70","author":"berg","year":"2011","journal-title":"Advanced Robotics"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5652073"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2651371"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32723-0_15"},{"key":"ref8","author":"sergeant","year":"0","journal-title":"Multimodal deep autoencoders for control of a mobile robot"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759428"},{"key":"ref2","article-title":"Reciprocal velocity obstacles for real-time multi-agent navigation","author":"berg","year":"2008","journal-title":"International Conference on Robotics and Automation (ICRA)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989182"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/027836499801700706"},{"key":"ref20","article-title":"Towards integrating hierarchical goal networks and motion planners to support planning for human-robot teams","author":"shivashankar","year":"2014","journal-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref22","author":"salman","year":"2018","journal-title":"Hierarchical reinforcement learning for sequencing behaviors"},{"key":"ref21","article-title":"Logic-geometric programming: an optimization-based approach to combined task and motion planning","author":"toussaint","year":"2015","journal-title":"International Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206505"},{"key":"ref23","first-page":"6","article-title":"Overview: A hierarchical framework for plan generation and execution in multirobot systems","volume":"6","author":"ma","year":"2018","journal-title":"IEEE Intelligent Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2794604"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2793889"}],"event":{"name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2018,12,12]]},"end":{"date-parts":[[2018,12,15]]}},"container-title":["2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8653250\/8664715\/08664803.pdf?arnumber=8664803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T02:50:15Z","timestamp":1598237415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8664803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/robio.2018.8664803","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}