{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:36:21Z","timestamp":1757608581537,"version":"3.44.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127932","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"16840-16846","source":"Crossref","is-referenced-by-count":1,"title":["CTSAC: Curriculum-Based Transformer Soft Actor-Critic for Goal-Oriented Robot Exploration"],"prefix":"10.1109","author":[{"given":"Chunyu","family":"Yang","sequence":"first","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology,Xuzhou,China,221116"}]},{"given":"Shengben","family":"Bi","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology,Xuzhou,China,221116"}]},{"given":"Yihui","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology,Xuzhou,China,221116"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology,Xuzhou,China,221116"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adf0970"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124466"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759289"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2005.i.009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2015.7324183"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21993"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981574"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463213"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793769"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160565"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR.2016.7784001"},{"key":"ref13","article-title":"Learning Exploration Policies for Navigation","author":"Chen","year":"2019","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Parisotto"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611590"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611247"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref18","article-title":"Efficient Recurrent OffPolicy RL Requires a Context-Encoder-Specific Learning Rate","author":"Luo","year":"2024","journal-title":"arXiv preprint arXiv:2405.15384"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3408271"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"issue":"181","key":"ref21","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.54364\/AAIML.2023.1170"},{"key":"ref24","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Machine Learning","author":"Haarnoja","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342066"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120630"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891991"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"102570","DOI":"10.1016\/j.rcim.2023.102570","article-title":"Distributed Deep Reinforcement Learning: An Overview","volume":"83","author":"Chang","year":"2023","journal-title":"Rob. Comput. Integr. Manuf."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3251193"},{"key":"ref30","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv preprint arXiv:1606.04671"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3133591"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911732"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611573"},{"key":"ref35","article-title":"Attention is All you Need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980479"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127932.pdf?arnumber=11127932","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:06:18Z","timestamp":1756879578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127932\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127932","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}