{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:20Z","timestamp":1766061620536,"version":"3.48.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100007694","name":"Korea Agency for Infrastructure Technology Advancement","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007694","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246186","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"13460-13467","source":"Crossref","is-referenced-by-count":0,"title":["SAC(\u03bb): Efficient Reinforcement Learning for Sparse-Reward Autonomous Car Racing using Imperfect Demonstrations"],"prefix":"10.1109","author":[{"given":"Heeseong","family":"Lee","sequence":"first","affiliation":[{"name":"Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungpyo","family":"Sagong","sequence":"additional","affiliation":[{"name":"Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minhyeong","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeongmin","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongjun","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926677"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21977"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811650"},{"key":"ref4","article-title":"F1tenth: An open-source evaluation environment for continuous control and reinforcement learning","volume-title":"Proceedings of Machine Learning Research","volume":"123","author":"O\u2019Kelly"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3240"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341731"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919880273"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.056"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562079"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064284"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295252"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3097345"},{"article-title":"Autonomous racing using a hybrid imitation-reinforcement learning architecture","year":"2021","author":"Samak","key":"ref15"},{"key":"ref16","article-title":"Hybrid policy optimization from imperfect demonstrations","volume":"36","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"205","article-title":"Positive-unlabeled reward learning","volume-title":"Conference on Robot Learning","author":"Xu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231224053"},{"key":"ref20","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460934"},{"key":"ref22","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967299"},{"key":"ref24","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197465"},{"issue":"6","key":"ref26","first-page":"2","article-title":"Torcs, the open racing car simulator","volume-title":"Software available","volume":"4","author":"Wymann","year":"2000"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2021.11.076"},{"key":"ref29","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning","volume-title":"International Conference on Learning Representations","author":"Kostrikov","key":"ref30"},{"key":"ref31","first-page":"1446","article-title":"Arc-actor residual critic for adversarial imitation learning","volume-title":"Conference on Robot Learning","author":"Deka"},{"key":"ref32","first-page":"2469","article-title":"Policy optimization with demonstrations","volume-title":"International conference on machine learning","author":"Kang"},{"key":"ref33","first-page":"3851","article-title":"Improving behavioural cloning with positive unlabeled learning","volume-title":"Conference on robot learning","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26222"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561049"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390286"},{"article-title":"Is discriminator a good feature extractor?","year":"2019","author":"Mao","key":"ref37"},{"key":"ref38","first-page":"24 725","article-title":"Discriminator-weighted offline imitation learning from suboptimal demonstrations","volume-title":"International Conference on Machine Learning","author":"Xu"},{"article-title":"Overcoming policy collapse in deep reinforcement learning","volume-title":"Sixteenth European Workshop on Reinforcement Learning","author":"Dohare","key":"ref39"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246186.pdf?arnumber=11246186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:35:56Z","timestamp":1766061356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246186","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}