{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T19:12:26Z","timestamp":1775934746846,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T00:00:00Z","timestamp":1702166400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T00:00:00Z","timestamp":1702166400000},"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":[[2023,12,10]]},"DOI":"10.1109\/wsc60868.2023.10408110","type":"proceedings-article","created":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T13:30:14Z","timestamp":1706707814000},"page":"1818-1829","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Agent Proximal Policy Optimization for a Deadlock Capable Transport System in a Simulation-Based Learning Environment"],"prefix":"10.1109","author":[{"given":"Marcel","family":"M\u00fcller","sequence":"first","affiliation":[{"name":"Otto von Guericke University Magdeburg,Institute of Logistics and Material Handling Systems,Magdeburg,Germany,39106"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorena S.","family":"Reyes-Rubiano","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Data & Business Analytics,Aachen,Germany,52072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tobias","family":"Reggelin","sequence":"additional","affiliation":[{"name":"Otto von Guericke University Magdeburg,Institute of Logistics and Material Handling Systems,Magdeburg,Germany,39106"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hartmut","family":"Zadek","sequence":"additional","affiliation":[{"name":"Otto von Guericke University Magdeburg,Institute of Logistics and Material Handling Systems,Magdeburg,Germany,39106"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"PPO Hyperparameters and Ranges","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2010.938363"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3372938.3372999"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916924"},{"key":"ref5","first-page":"17057","article-title":"\u201cCombining Deep Reinforcement Learning and Search for Imperfect-Information Games","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1049\/ip-sen:19971023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10614-021-10119-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/356586.356588"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/70.370500"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/00207540110118073"},{"key":"ref12","volume-title":"Multi-Agent Systems: An Introduction to Distributed Artificial Intelligence","volume":"1","author":"Ferber","year":"1999"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29908-8_58"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/00207540701441921"},{"key":"ref16","article-title":"\u201cRay rllib: A Composable and Scalable Reinforcement Learning Library","volume":"85","author":"Liang","year":"2017","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.7148\/2017-0169"},{"key":"ref18","article-title":"\u201cMulti-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","author":"Lowe","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"\u201cPlaying Atari with Deep Reinforcement Learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WSC57314.2022.10015270"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WSC40007.2019.9004740"},{"key":"ref22","article-title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","volume":"1","author":"Papoudakis"},{"issue":"1","key":"ref23","first-page":"7234","article-title":"\u201cMonotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","volume":"21","author":"Rashid","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308584"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2003.820572"},{"key":"ref26","article-title":"\u201cThe StarCraft Multi-Agent Challenge","volume":"abs\/1902.04043","author":"Samvelyan","year":"2019","journal-title":"CoRR"},{"key":"ref27","article-title":"\u201cProximal Policy Optimization Algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-190613"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref32","volume-title":"Modern Operating Systems","author":"Tanenbaum","year":"2022"},{"key":"ref33","first-page":"15032","article-title":"Pettingzoo: Gym for Multi-Agent Reinforcement Learning","volume":"34","author":"Terry","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIMSA.2017.7985596"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref36","first-page":"24611","article-title":"The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"}],"event":{"name":"2023 Winter Simulation Conference (WSC)","location":"San Antonio, TX, USA","start":{"date-parts":[[2023,12,10]]},"end":{"date-parts":[[2023,12,13]]}},"container-title":["2023 Winter Simulation Conference (WSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10406299\/10407113\/10408110.pdf?arnumber=10408110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T03:17:55Z","timestamp":1709435875000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10408110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,10]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/wsc60868.2023.10408110","relation":{},"subject":[],"published":{"date-parts":[[2023,12,10]]}}}