{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T16:15:21Z","timestamp":1773850521845,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"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\/501100004204","name":"Tongji University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004204","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,2]]},"DOI":"10.1109\/iv55156.2024.10588651","type":"proceedings-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T17:19:28Z","timestamp":1721063968000},"page":"2667-2673","source":"Crossref","is-referenced-by-count":8,"title":["Random Network Distillation Based Deep Reinforcement Learning for AGV Path Planning"],"prefix":"10.1109","author":[{"given":"Huilin","family":"Yin","sequence":"first","affiliation":[{"name":"Tongji University,School of Electronic and Information Engineering,Shanghai,China"}]},{"given":"Shengkai","family":"Su","sequence":"additional","affiliation":[{"name":"Tongji University,School of Electronic and Information Engineering,Shanghai,China"}]},{"given":"Yinjia","family":"Lin","sequence":"additional","affiliation":[{"name":"Tongji University,School of Electronic and Information Engineering,Shanghai,China"}]},{"given":"Pengju","family":"Zhen","sequence":"additional","affiliation":[{"name":"Tongji University,School of Electronic and Information Engineering,Shanghai,China"}]},{"given":"Karin","family":"Festl","sequence":"additional","affiliation":[{"name":"Graz University of Technology,Virtual Vehicle Research GmbH,Graz,Austria,8010"}]},{"given":"Daniel","family":"Watzenig","sequence":"additional","affiliation":[{"name":"Graz University of Technology,Virtual Vehicle Research GmbH,Graz,Austria,8010"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2018.8483306"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2019.12.002"},{"key":"ref3","article-title":"Review on Intelligent Path Planning Algorithm of Mobile Robots","author":"Chun-Ying","year":"2024","journal-title":"Transducer and Microsystem Technologies"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1117\/12.2689523"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3482632.3484036"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.protcy.2016.03.010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2018.12.001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.compstruc.2018.08.016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3020024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106960"},{"issue":"1","key":"ref11","first-page":"103","article-title":"Reinforcement Learning: An Introduction","volume":"21","author":"Sutton","year":"2000","journal-title":"AI Magazine"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCONS.2018.8663020"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning. Machine Learning","volume":"8","author":"Christopher","year":"1992","journal-title":"Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref16","article-title":"Playing Atari with Deep Reinforcement Learning","author":"Mnih","year":"2013","journal-title":"Computer Science"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1049\/trit.2020.0024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.01.054"},{"key":"ref19","article-title":"Proximal Policy Optimization Algorithms","author":"Schulman","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/s23136101"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CASE56687.2023.10260579"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186577"},{"key":"ref23","article-title":"Policy Invariance under Reward Transformations: Theory and Application to Reward Shaping","volume-title":"International Conference on Machine Learning","volume":"99","author":"Ng"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.112147"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848046"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3461353.3461365"}],"event":{"name":"2024 IEEE Intelligent Vehicle Symposium (IV)","location":"Jeju Island, Korea, Republic of","start":{"date-parts":[[2024,6,2]]},"end":{"date-parts":[[2024,6,5]]}},"container-title":["2024 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10587320\/10588370\/10588651.pdf?arnumber=10588651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T05:09:48Z","timestamp":1721365788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10588651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,2]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iv55156.2024.10588651","relation":{},"subject":[],"published":{"date-parts":[[2024,6,2]]}}}