{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:35:47Z","timestamp":1785512147375,"version":"3.56.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/iv64158.2025.11097638","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:54:55Z","timestamp":1754502895000},"page":"2325-2332","source":"Crossref","is-referenced-by-count":4,"title":["Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Alkis","family":"Sygkounas","sequence":"first","affiliation":[{"name":"Center for Applied Autonomous Sensor Systems (AASS), Örebro University,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioannis","family":"Athanasiadis","sequence":"additional","affiliation":[{"name":"Linköping University,Computer Vision Laboratory,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Persson","sequence":"additional","affiliation":[{"name":"Center for Applied Autonomous Sensor Systems (AASS), Örebro University,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Felsberg","sequence":"additional","affiliation":[{"name":"Linköping University,Computer Vision Laboratory,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amy","family":"Loutfi","sequence":"additional","affiliation":[{"name":"Center for Applied Autonomous Sensor Systems (AASS), Örebro University,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.05.014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3452480"},{"key":"ref3","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Machine Learning","author":"Wang","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.102"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.05.017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref8","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Prioritized Experience Replay","author":"Tom","year":"2015","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ivs.2016.7535377"},{"key":"ref11","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proceedings of the In-ternational Conference on Machine Learning (ICML)","author":"Scott","year":"2018"},{"key":"ref12","article-title":"Behavioral cloning from observation","author":"Faraz","year":"2018","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2996274"},{"key":"ref15","volume-title":"Human-in-the-Loop Machine Learning: Active learning and annotation for human-centered AI","author":"Monarch","year":"2021"},{"key":"ref16","article-title":"Human-in-the-loop deep reinforcement learning with application to autonomous driving","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3210490"},{"key":"ref19","article-title":"Dqn-tamer: Human-in-the-loop reinforcement learning with intractable feedback","author":"Arakawa","year":"2018","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"16","article-title":"Distributed deep reinforcement learning on the cloud for autonomous driving","volume-title":"Proc. 1 st Int. Workshop on Software Engineering for AI in Autonomous Systems","author":"Spryn","year":"2018"},{"key":"ref21","author":"Salvador","year":"2019","journal-title":"Autonomous Driving via Deep Reinforcement Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2014.6926319"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9283-7"},{"key":"ref24","article-title":"Efficient learning of safe driving policy via human-ai copilot optimization","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref26","article-title":"REvolve: Reward Evolution with Large Language Models for Autonomous Driving","author":"Hazra","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"}],"event":{"name":"2025 IEEE Intelligent Vehicles Symposium (IV)","location":"Cluj-Napoca, Romania","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11097351\/11097337\/11097638.pdf?arnumber=11097638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T05:21:42Z","timestamp":1754544102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11097638\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iv64158.2025.11097638","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}