{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T11:52:55Z","timestamp":1769169175902,"version":"3.49.0"},"reference-count":50,"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\/icra55743.2025.11127813","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"6756-6763","source":"Crossref","is-referenced-by-count":2,"title":["DemoStart: Demonstration-Led Auto-Curriculum Applied to Sim-to-Real with Multi-Fingered Robots"],"prefix":"10.1109","author":[{"given":"Maria","family":"Bauza","sequence":"first","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose Enriaue","family":"Chen","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valentin","family":"Dalibard","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nimrod","family":"Gileadi","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roland","family":"Hafner","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murilo F.","family":"Martins","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joss","family":"Moore","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rugile","family":"Pevceviciute","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antoine","family":"Laurens","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dushyant","family":"Rao","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martina","family":"Zambelli","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Riedmiller","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jon","family":"Scholz","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Bousmalis","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Nori","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Heess","sequence":"additional","affiliation":[{"name":"Google DeepMind."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref2","article-title":"Robocat: A self-improving generalist agent for robotic manipulation","volume-title":"Transactions on Machine Learning Research","author":"Bousmalis","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref4","article-title":"Deft: Dexterous fine-tuning for real-world hand policies","author":"Kannan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Aloha 2: An enhanced low-cost hardware for bimanual teleoperation","author":"Aldaco","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8808"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802181"},{"key":"ref8","article-title":"Visual dexterity: In-hand dexterous manipulation from depth","volume-title":"ICML workshop on new frontiers in learning, control, and dynamical systems","author":"Chen","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.089"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00360"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.037"},{"key":"ref12","article-title":"Dexterous in-hand manipulation by guiding exploration with simple sub-skill controllers","author":"Khandate","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145961"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487156"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.036"},{"key":"ref17","first-page":"2549","article-title":"General in-hand object rotation with vision and touch","volume-title":"Conference on Robot Learning","author":"Qi"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802864"},{"key":"ref19","article-title":"Learning from demonstration","volume":"9","author":"Schaal","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref22","author":"Akkaya","year":"2019","journal-title":"Solving rubik\u2019s cube with a robot hand"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.039"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981458"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160216"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981730"},{"key":"ref27","first-page":"66","article-title":"Learning by cheating","volume-title":"Conference on Robot Learning","author":"Chen"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/671"},{"key":"ref29","article-title":"Emergent complexity and zero-shot transfer via unsupervised environment design","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS \u201920","author":"Dennis"},{"key":"ref30","first-page":"4940","article-title":"Prioritized level replay","volume-title":"International Conference on Machine Learning","author":"Jiang"},{"key":"ref31","article-title":"Open-ended learning leads to generally capable agents","author":"Team","year":"2021","journal-title":"arXiv preprint"},{"key":"ref32","first-page":"1887","article-title":"Human-timescale adaptation in an open-ended task space","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"202","author":"Bauer"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00313"},{"key":"ref34","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","volume-title":"Conference on robot learning","author":"Florensa"},{"key":"ref35","author":"Popov","year":"2017","journal-title":"Data-efficient deep reinforcement learning for dexterous manipulation"},{"key":"ref36","article-title":"Learning montezuma\u2019s revenge from a single demonstration","author":"Salimans","year":"2018","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref38","volume-title":"Backplay: \u2019man muss immer umkehren","author":"Resnick","year":"2019"},{"key":"ref39","article-title":"Reverse forward curriculum learning for extreme sample and demonstration efficiency in reinforcement learning","author":"Tao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","first-page":"1407","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","volume-title":"International conference on machine learning","author":"Espeholt"},{"key":"ref41","article-title":"Reinforcement learning for robots using neural networks","author":"Lin","year":"1992","journal-title":"Carnegie Mellon University"},{"key":"ref42","article-title":"Maximum a posteriori policy optimisation","author":"Abdolmaleki","year":"2018","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref44","volume-title":"Filament (1.52.0) - real-time physically based rendering engine","year":"2024"},{"key":"ref45","author":"Springenberg","year":"2024","journal-title":"Offline actor-critic reinforcement learning scales to large models"},{"key":"ref46","volume-title":"Dex-ee","year":"2024"},{"key":"ref47","volume-title":"Assembly Performance Metrics and Test Methods","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917700714"},{"key":"ref49","volume-title":"Spacemouse wireless","year":"2024"},{"key":"ref50","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"80","author":"Riedmiller"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"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\/11127813.pdf?arnumber=11127813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:11:43Z","timestamp":1756879903000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127813\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127813","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}