{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T15:56:44Z","timestamp":1781107004652,"version":"3.54.1"},"reference-count":28,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Robotics and Autonomous Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.robot.2026.105499","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T12:45:50Z","timestamp":1778244350000},"page":"105499","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SPARS: Structure-informed progress-aware reward shaping for fabric manipulation learning from demonstration"],"prefix":"10.1016","volume":"203","author":[{"given":"Ruhan","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5289-7857","authenticated-orcid":false,"given":"Yifei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianqing","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianyi","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.robot.2026.105499_b1","first-page":"5872","article-title":"Cloth funnels: Canonicalized-alignment for multi-purpose garment manipulation","author":"Canberk","year":"2023","journal-title":"IEEE Int. Conf. Robot. Autom. (ICRA)"},{"key":"10.1016\/j.robot.2026.105499_b2","series-title":"Conference on Robot Learning","article-title":"Softgym: Benchmarking deep reinforcement learning for deformable object manipulation","author":"Lin","year":"2020"},{"key":"10.1016\/j.robot.2026.105499_b3","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1109\/TRO.2020.2986921","article-title":"A grasping-centered analysis for cloth manipulation","volume":"36","author":"Borr\u00e0s","year":"2019","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.robot.2026.105499_b4","series-title":"AAAI Conference on Artificial Intelligence","article-title":"Subspace-aware exploration for sparse-reward multi-agent tasks","author":"Xu","year":"2023"},{"key":"10.1016\/j.robot.2026.105499_b5","series-title":"AAAI Conference on Artificial Intelligence","doi-asserted-by":"crossref","DOI":"10.5772\/intechopen.107726","article-title":"Stas: Spatial-temporal return decomposition for solving sparse rewards problems in multi-agent reinforcement learning","author":"Chen","year":"2024"},{"key":"10.1016\/j.robot.2026.105499_b6","doi-asserted-by":"crossref","first-page":"8775","DOI":"10.1109\/LRA.2022.3187843","article-title":"Learning deformable object manipulation from expert demonstrations","volume":"7","author":"Salhotra","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105499_b7","article-title":"On covariate shift of latent confounders in imitation and reinforcement learning","author":"Tennenholtz","year":"2021","journal-title":"Int. Conf. Learn. Represent. (ICLR)"},{"key":"10.1016\/j.robot.2026.105499_b8","series-title":"International Conference on Machine Learning","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"Ng","year":"1999"},{"key":"10.1016\/j.robot.2026.105499_b9","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1146\/annurev-control-100819-063206","article-title":"Recent advances in robot learning from demonstration","volume":"3","author":"chaandar Ravichandar","year":"2020","journal-title":"Annu. Rev. Control. Robot. Auton. Syst."},{"key":"10.1016\/j.robot.2026.105499_b10","series-title":"International Conference on Machine Learning","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"Finn","year":"2016"},{"key":"10.1016\/j.robot.2026.105499_b11","series-title":"Curriculum learning for reinforcement learning domains: A framework and survey","author":"Narvekar","year":"2020"},{"key":"10.1016\/j.robot.2026.105499_b12","series-title":"4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings","article-title":"Prioritized experience replay","author":"Schaul","year":"2016"},{"key":"10.1016\/j.robot.2026.105499_b13","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/TPAMI.2023.3319005","article-title":"Re-thinking the effectiveness of batch normalization and beyond","volume":"46","author":"Peng","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.robot.2026.105499_b14","doi-asserted-by":"crossref","DOI":"10.1126\/scirobotics.abd8803","article-title":"Modeling, learning, perception, and control methods for deformable object manipulation","volume":"6","author":"Yin","year":"2021","journal-title":"Sci. Robot."},{"key":"10.1016\/j.robot.2026.105499_b15","series-title":"International Symposium of Robotics Research","article-title":"Deep transfer learning of pick points on fabric for robot bed-making","author":"Seita","year":"2018"},{"key":"10.1016\/j.robot.2026.105499_b16","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"9553","article-title":"Cloth region segmentation for robust grasp selection","author":"Qian","year":"2020"},{"key":"10.1016\/j.robot.2026.105499_b17","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"4889","article-title":"Learning to grasp clothing structural regions for garment manipulation tasks","author":"Chen","year":"2023"},{"key":"10.1016\/j.robot.2026.105499_b18","series-title":"One policy to dress them all: Learning to dress people with diverse poses and garments","author":"Wang","year":"2023"},{"key":"10.1016\/j.robot.2026.105499_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.compind.2024.104216","article-title":"A robotic skill transfer learning framework of dynamic manipulation for fabric placement","volume":"165","author":"Fu","year":"2025","journal-title":"Comput. Ind."},{"key":"10.1016\/j.robot.2026.105499_b20","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1109\/LRA.2020.2965891","article-title":"Benchmarking bimanual cloth manipulation","volume":"5","author":"Garcia-Camacho","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105499_b21","series-title":"Conference on Robot Learning","article-title":"Flingbot: The unreasonable effectiveness of dynamic manipulation for cloth unfolding","author":"Ha","year":"2021"},{"key":"10.1016\/j.robot.2026.105499_b22","series-title":"Dextairity: Deformable manipulation can be a breeze","author":"Xu","year":"2022"},{"key":"10.1016\/j.robot.2026.105499_b23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3054912","article-title":"Imitation learning: A survey of learning methods","volume":"50","author":"Hussein","year":"2017","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.robot.2026.105499_b24","series-title":"Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020"},{"key":"10.1016\/j.robot.2026.105499_b25","first-page":"5639","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","volume":"119","author":"Laskin","year":"2020","journal-title":"Proc. 37th Int. Conf. Mach. Learn."},{"key":"10.1016\/j.robot.2026.105499_b26","doi-asserted-by":"crossref","first-page":"2455","DOI":"10.1109\/LRA.2024.3358750","article-title":"Trakdis: A transformer-based knowledge distillation approach for visual reinforcement learning with application to cloth manipulation","volume":"9","author":"Chen","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.robot.2026.105499_b27","series-title":"Neural Information Processing Systems","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","author":"Kumar","year":"2019"},{"key":"10.1016\/j.robot.2026.105499_b28","series-title":"Layer normalization","author":"Ba","year":"2016"}],"container-title":["Robotics and Autonomous Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889026001727?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889026001727?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T14:57:49Z","timestamp":1781103469000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0921889026001727"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":28,"alternative-id":["S0921889026001727"],"URL":"https:\/\/doi.org\/10.1016\/j.robot.2026.105499","relation":{"is-supplemented-by":[{"id-type":"uri","id":"https:\/\/github.com\/yif2001\/syndom-coordinated-component-optimization-for-dom","asserted-by":"subject"}]},"ISSN":["0921-8890"],"issn-type":[{"value":"0921-8890","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SPARS: Structure-informed progress-aware reward shaping for fabric manipulation learning from demonstration","name":"articletitle","label":"Article Title"},{"value":"Robotics and Autonomous Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.robot.2026.105499","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"105499"}}