{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T09:48:43Z","timestamp":1756460923933,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610641","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"7412-7418","source":"Crossref","is-referenced-by-count":1,"title":["Improving the Generalization of Unseen Crowd Behaviors for Reinforcement Learning based Local Motion Planners"],"prefix":"10.1109","author":[{"given":"Wen Zheng","family":"Terence Ng","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}]},{"given":"Jianda","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}]},{"given":"Sinno Jialin","family":"Pan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Tianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-62533-1_1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2869644"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196785"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891491"},{"key":"ref9","first-page":"4221","article-title":"Crowdsteer: Realtime smooth and collision-free robot navigation in densely crowded scenarios trained using high-fidelity simulation","volume-title":"Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence","author":"Liang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197148"},{"journal-title":"R-sarl: Crowd-aware navigation based deep reinforcement learning for nonholonomic robot in complex environments","year":"2021","author":"Zhou","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068662"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/027836499801700706"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2849942"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341805"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974695"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561973"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920916531"},{"key":"ref21","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"International conference on machine learning","author":"Haarnoja"},{"article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"International Conference on Learning Representations","author":"Eysenbach","key":"ref22"},{"key":"ref23","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"29","author":"Foerster","year":"2016","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref25","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"article-title":"Social diversity and social preferences in mixed-motive reinforcement learning","year":"2020","author":"McKee","key":"ref26"},{"key":"ref27","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Learning to coordinate manipulation skills via skill behavior diversification","volume-title":"International conference on learning representations","author":"Lee","key":"ref28"},{"key":"ref29","article-title":"The im algorithm: a variational approach to information maximization","author":"Barber","year":"2004","journal-title":"NeurIPS"},{"journal-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref30"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref31"},{"journal-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-008-0014-4"},{"key":"ref34","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","volume-title":"Proceedings of the 27th international conference on machine learning (ICML-10)","author":"Nair"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2022.3190086","article-title":"Arena-bench: A benchmarking suite for obstacle avoidance approaches in highly dynamic environments","author":"K\u00e4stner","year":"2022"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610641.pdf?arnumber=10610641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:21:19Z","timestamp":1723267279000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610641","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}