{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:10:46Z","timestamp":1783815046269,"version":"3.55.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"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":[[2024,6,2]]},"DOI":"10.1109\/iv55156.2024.10588380","type":"proceedings-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T17:19:28Z","timestamp":1721063968000},"page":"1686-1692","source":"Crossref","is-referenced-by-count":2,"title":["Using Petri Nets as an Integrated Constraint Mechanism for Reinforcement Learning Tasks"],"prefix":"10.1109","author":[{"given":"Timon","family":"Sachweh","sequence":"first","affiliation":[{"name":"TU Dortmund University,Faculty of Computer Science, Chair of Artificial Intelligence,Dortmund,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre","family":"Haritz","sequence":"additional","affiliation":[{"name":"TU Dortmund University,Faculty of Computer Science, Chair of Artificial Intelligence,Dortmund,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Liebig","sequence":"additional","affiliation":[{"name":"TU Dortmund University,Faculty of Computer Science, Chair of Artificial Intelligence,Dortmund,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Safe reinforcement learning via shielding","author":"Alshiekh","year":"2017","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0070"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAE.2010.5451406"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/45.329294"},{"key":"ref5","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2004.838180"},{"key":"ref7","first-page":"290","article-title":"A learning petri net model based on reinforcement learning","volume-title":"Proceedings of the 15th International Symposium on Artificial Life and Robotics (AROB2010)","author":"Feng"},{"issue":"1","key":"ref8","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)52677-4"},{"key":"ref10","article-title":"Using a deep reinforcement learning agent for traffic signal control","author":"Genders","year":"2016"},{"key":"ref11","article-title":"A review of safe reinforcement learning: Methods, theory and applications","author":"Gu","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2020.02.004"},{"key":"ref13","article-title":"Scoot-a traffic responsive method of coordinating signals. Technical report, Transport and Road Research Laboratory","author":"Hunt","year":"1981"},{"key":"ref14","article-title":"Deep constrained q-learning","author":"Kalweit","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25808-9_4"},{"key":"ref17","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/5.24143"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SII55687.2023.10039301"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78424-9_51"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1404.7828"},{"key":"ref22","article-title":"skrl: Modular and flexible library for reinforcement learning","author":"Serrano-Mu\u00f1oz","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-020-00326-5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10399"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1201\/9780429184185"}],"event":{"name":"2024 IEEE Intelligent Vehicle Symposium (IV)","location":"Jeju Island, Korea, Republic of","start":{"date-parts":[[2024,6,2]]},"end":{"date-parts":[[2024,6,5]]}},"container-title":["2024 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10587320\/10588370\/10588380.pdf?arnumber=10588380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T05:25:07Z","timestamp":1721366707000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10588380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,2]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iv55156.2024.10588380","relation":{},"subject":[],"published":{"date-parts":[[2024,6,2]]}}}