{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T02:04:18Z","timestamp":1740103458620,"version":"3.37.3"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,18]],"date-time":"2024-08-18T00:00:00Z","timestamp":1723939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,18]],"date-time":"2024-08-18T00:00:00Z","timestamp":1723939200000},"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","award":["62203334"],"award-info":[{"award-number":["62203334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013105","name":"Shanghai Rising-Star Program","doi-asserted-by":"publisher","award":["22YF1451300"],"award-info":[{"award-number":["22YF1451300"]}],"id":[{"id":"10.13039\/501100013105","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,8,18]]},"DOI":"10.1109\/indin58382.2024.10774316","type":"proceedings-article","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T19:05:07Z","timestamp":1734030307000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Value Conditional State Entropy Reinforcement Learning for Autonomous Driving Decision Making"],"prefix":"10.1109","author":[{"given":"Yiyi","family":"Han","sequence":"first","affiliation":[{"name":"Tongji University,Department of Control Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lulu","family":"Guo","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Control Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Chen","sequence":"additional","affiliation":[{"name":"Tongji University, School of Automotive Studies,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20255"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3435937"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995727"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref8","first-page":"1861","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Haarnoja","year":"2024"},{"key":"ref9","first-page":"9443","article-title":"State Entropy Maximization with Random Encoders for Efficient Exploration","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Seo","year":"2024"},{"key":"ref10","article-title":"Never Give Up: Learning Directed Exploration Strategies","author":"Badia","year":"2020","journal-title":"arXiv"},{"key":"ref11","article-title":"Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration","volume":"36","author":"Kim","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.066138"},{"volume-title":"[PDF] Machine learning - a probabilistic perspective | Semantic Scholar","year":"2024","key":"ref14"},{"key":"ref15","first-page":"2555","article-title":"Learning Latent Dynamics for Planning from Pixels","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Hafner","year":"2024"},{"key":"ref16","first-page":"741","article-title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","volume-title":"Advances in Neural Information Processing Systems","author":"Lee","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref18","article-title":"If MaxEnt RL is the Answer, What is the Question?","author":"Eysenbach","year":"2019","journal-title":"ArXiv"},{"key":"ref19","article-title":"CARLA: An Open Urban Driving Simulator","author":"Dosovitskiy","year":"2017","journal-title":"arXiv"}],"event":{"name":"2024 IEEE 22nd International Conference on Industrial Informatics (INDIN)","start":{"date-parts":[[2024,8,18]]},"location":"Beijing, China","end":{"date-parts":[[2024,8,20]]}},"container-title":["2024 IEEE 22nd International Conference on Industrial Informatics (INDIN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10774078\/10774079\/10774316.pdf?arnumber=10774316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T06:36:38Z","timestamp":1734158198000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10774316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,18]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/indin58382.2024.10774316","relation":{},"subject":[],"published":{"date-parts":[[2024,8,18]]}}}