{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T13:12:20Z","timestamp":1793020340500,"version":"4.5.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"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":[[2022,10,8]]},"DOI":"10.1109\/itsc55140.2022.9922306","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:40:13Z","timestamp":1667526013000},"page":"951-958","source":"Crossref","is-referenced-by-count":13,"title":["Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Masking"],"prefix":"10.1109","author":[{"given":"Arthur","family":"Muller","sequence":"first","affiliation":[{"name":"Fraunhofer Center for Machine Learning and Fraunhofer IOSB-INA,Lemgo,Germany,32657"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthia","family":"Sabatelli","sequence":"additional","affiliation":[{"name":"University of Groningen,Department of Artificial Intelligence and Cognitive Engineering,Groningen,The Netherlands,9712CP"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","author":"huang","year":"2020","journal-title":"A closer look at invalid action masking in policy gradient algorithms"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294259"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref15","first-page":"77","article-title":"The Human Factor in Road Traffic City","volume":"1","author":"prasolenko","year":"2015","journal-title":"International Journal of Intelligent Control and Automation"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2001.948804"},{"key":"ref20","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref11","author":"genders","year":"2018","journal-title":"Reinforcement Learning For Adaptive Traffic Signal Control"},{"key":"ref22","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"0","journal-title":"4th International Conference on Learning Representations ICLR 2016 - Conference Track Proceedings"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref21","first-page":"4768","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume":"7","author":"liang","year":"0","journal-title":"ICML 2018-35th International Conference on Machine Learning"},{"key":"ref2","first-page":"1","article-title":"Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey","author":"haydari","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref1","article-title":"Urban Mobility Report 2019","author":"schrank","year":"2019","journal-title":"TheTexasA&MTransportationInstitute"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/INDIN41052.2019.8972264"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0191-8869(99)00249-4"},{"key":"ref19","article-title":"Distributed Prioritized Experience Replay","author":"horgan","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref18","first-page":"1407","article-title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","author":"espeholt","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref8","first-page":"8","article-title":"Coordinated deep reinforcement learners for traffic light control","author":"van der pol","year":"0","journal-title":"30th Conference on Neural Information Processing Systems (NIPS 2016)"},{"key":"ref7","year":"2015","journal-title":"Forschungsgesellschaft für Straßen- und Verkehrswesen Ed Richtlinien für Lichtsignalanlagen RiLSA Lichtzeichenanlagen für den Straßenverkehr"},{"key":"ref9","author":"gao","year":"2017","journal-title":"Adaptive Traffic Signal Control Deep Reinforcement Learning Algorithm with Experience Replay and Target Network"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231687"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3068287"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA52953.2021.00085"}],"event":{"name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","location":"Macau, China","start":{"date-parts":[[2022,10,8]]},"end":{"date-parts":[[2022,10,12]]}},"container-title":["2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9921415\/9921739\/09922306.pdf?arnumber=9922306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T23:11:21Z","timestamp":1677539481000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9922306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,8]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/itsc55140.2022.9922306","relation":{},"subject":[],"published":{"date-parts":[[2022,10,8]]}}}