{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:32:51Z","timestamp":1763191971878,"version":"3.45.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228922","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Fuzzy Knowledge-Driven Human-in-the-Loop Learning for Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Yiming","family":"Zeng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xichong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Huang","sequence":"additional","affiliation":[{"name":"China Ship Development and Design Center,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjun","family":"Xiao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940562"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2983149"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.sna.2021.112566"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2913998"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2957797"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123378"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3170122"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3450267.3450542"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref12","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods[C]","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827073"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.056"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/machines10080609"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2014.09.015"},{"key":"ref18","first-page":"9133","article-title":"Responsive safety in reinforcement learning by pid lagrangian methods[C]","volume-title":"International Conference on Machine Learning","author":"Stooke"},{"key":"ref19","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping[C]","volume-title":"Icml","volume":"99","author":"Ng"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3074535"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2016.2565718"},{"issue":"12","key":"ref22","first-page":"11764","article-title":"A hierarchical decision-making framework for autonomous driving based on automatic rules generation and evaluation[J]","volume":"68","author":"Chen","year":"2019","journal-title":"IEEE Transactions on Vehicular Technology"},{"article-title":"End to end learning for self-driving cars[J]","year":"2016","author":"Bojarski","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref25","first-page":"22","article-title":"Constrained policy optimization[C]","volume-title":"International conference on machine learning","author":"Achiam"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5132"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017940631555"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"issue":"2","key":"ref30","first-page":"2","article-title":"Algorithms for inverse reinforcement learning[C]","volume-title":"Icml","volume":"1","author":"Ng"},{"key":"ref31","article-title":"Generative adversarial imitation learning[J]","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Dqn-tamer: Human-in-the-loop reinforcement learning with intractable feedback[J]","year":"2018","author":"Arakawa","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-021-10006-9"},{"key":"ref35","first-page":"3053","article-title":"RLlib: Abstractions for distributed reinforcement learning[C]","volume-title":"International conference on machine learning","author":"Liang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"article-title":"Soft actor-critic algorithms and applications[J]","year":"2018","author":"Haarnoja","key":"ref37"},{"key":"ref38","first-page":"24432","article-title":"Model-based safe deep reinforcement learning via a constrained proximal policy optimization algorithm[J]","volume":"35","author":"Jayant","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.120272"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228922.pdf?arnumber=11228922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:44Z","timestamp":1763191724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228922\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228922","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}