{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T19:47:48Z","timestamp":1767815268548,"version":"3.49.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,12]]},"DOI":"10.1109\/indin64977.2025.11278962","type":"proceedings-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:33:35Z","timestamp":1767724415000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["IDM-TD3: An Improved Reinforcement Learning Algorithm Based on Inverse Dynamic Model"],"prefix":"10.1109","author":[{"given":"Yichen","family":"Luo","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology,Department of Intelligent Systems,Stockholm,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dayang","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology,School of Transportation and Logistics Engineering,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanghang","family":"Zeng","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Department of Intelligent Systems,Stockholm,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong-Liverpool University,School of Advanced Technology,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibo","family":"Pang","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Department of Intelligent Systems,Stockholm,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Continuous control with deep reinforcement learning","volume-title":"4th International Conference on Learning Representations (ICLR)","author":"Lillicrap"},{"key":"ref2","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning (ICML)","author":"Mnih"},{"key":"ref3","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14174"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref8","article-title":"Progressive neural networks","author":"Rusu","year":"2022"},{"key":"ref9","article-title":"Sim-to-real robot learning from pixels with progressive nets","volume-title":"1st Conference on Robot Learning (CoRL)","author":"Rusu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref12","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","volume-title":"5rd International Conference on Learning Representations (ICLR)","author":"Gupta"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref14","article-title":"Policy optimization with demonstrations","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)","author":"Kang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref16","article-title":"Pathnet: Evolution channels gradient descent in super neural networks","author":"Fernando","year":"2017"},{"key":"ref17","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"Christiano","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509858"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref20","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)","author":"Fujimoto"},{"key":"ref21","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proceedings of the 31st International Conference on International Conference on Machine Learning (ICML)","author":"Silver"},{"key":"ref22","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref25","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref28","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume-title":"Proceedings of the 1st International Conference on Neural Information Processing Systems (NeurIPS)","author":"Pomerleau"},{"key":"ref29","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS)","author":"Fujimoto"},{"key":"ref30","article-title":"Openai baselines","author":"Dhariwal","year":"2017"}],"event":{"name":"2025 IEEE 23rd International Conference on Industrial Informatics (INDIN)","location":"Kunming, China","start":{"date-parts":[[2025,7,12]]},"end":{"date-parts":[[2025,7,15]]}},"container-title":["2025 IEEE 23rd International Conference on Industrial Informatics (INDIN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11278897\/11278845\/11278962.pdf?arnumber=11278962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T18:30:37Z","timestamp":1767810637000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11278962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,12]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/indin64977.2025.11278962","relation":{},"subject":[],"published":{"date-parts":[[2025,7,12]]}}}