{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T09:19:48Z","timestamp":1778318388842,"version":"3.51.4"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"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":[[2024,9,24]]},"DOI":"10.1109\/itsc58415.2024.10919918","type":"proceedings-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T19:00:11Z","timestamp":1742583611000},"page":"768-775","source":"Crossref","is-referenced-by-count":3,"title":["SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning"],"prefix":"10.1109","author":[{"given":"Jianye","family":"Xu","sequence":"first","affiliation":[{"name":"RWTH Aachen University,Chair of Embedded Software (Informatik 11),Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Hu","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Department of Computer Science,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bassam","family":"Alrifaee","sequence":"additional","affiliation":[{"name":"University of the Bundeswehr Munich,Department of Aerospace Engineering,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref2","article-title":"Generalization and regularization in DQN","author":"Farebrother","year":"2020","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"},{"key":"ref4","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref7","article-title":"A deeper look at experience replay","author":"Zhang","year":"2018","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Prioritized experience replay","volume-title":"International Conference on Learning Representations (ICLR)","author":"Schaul","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adg1462"},{"key":"ref11","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Buckman","year":"2018"},{"key":"ref12","article-title":"Is a good representation sufficient for sample efficient reinforcement learning?","volume-title":"International Conference on Learning Representations","author":"Du","year":"2020"},{"key":"ref13","article-title":"As-sessing generalization in deep reinforcement learning","author":"Packer","year":"2019","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proceedings of The 33rd International Conference on Machine Learning","author":"Mnih","year":"2016"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"EPOpt: Learning robust neural network policies using model ensembles","volume-title":"International Conference on Learning Representations (ICLR)","author":"Rajeswaran","year":"2017"},{"key":"ref17","first-page":"1282","article-title":"Quanti-fying generalization in reinforcement learning","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Cobbe","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref19","article-title":"Transient non-stationarity and generalisation in deep reinforcement learning","volume-title":"International Conference on Learning Representations","author":"IgI","year":"2020"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1613\/jair.1.14174","article-title":"A survey of zero-shot generalisation in deep reinforcement learning","volume":"76","author":"Kirk","year":"2023","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref23","first-page":"709","article-title":"Dynamic programming for partially observable stochastic games","author":"Hansen","year":"2024","journal-title":"American Association for Artificial Intelligence"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref25","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Lowe","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4095-0_11"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-51497-5_4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/ECC54610.2021.9654986"},{"key":"ref29","volume-title":"Vehicle Dynamics and Control, ser. Mechanical Engineering Series","author":"Rajamani","year":"2006"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2019.2901089"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.031"},{"key":"ref32","volume-title":"Reinforcement Learning: An Intro-duction","author":"Sutton","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2014.6856487"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569929"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2008.80"}],"event":{"name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","location":"Edmonton, AB, Canada","start":{"date-parts":[[2024,9,24]]},"end":{"date-parts":[[2024,9,27]]}},"container-title":["2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10919469\/10919190\/10919918.pdf?arnumber=10919918","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T21:01:39Z","timestamp":1742590899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10919918\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,24]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/itsc58415.2024.10919918","relation":{},"subject":[],"published":{"date-parts":[[2024,9,24]]}}}