{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:19:19Z","timestamp":1787012359299,"version":"build-2736575974"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341727","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Active Task Randomization: Learning Robust Skills via Unsupervised Generation of Diverse and Feasible Tasks"],"prefix":"10.1109","author":[{"given":"Kuan","family":"Fang","sequence":"first","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toki","family":"Migimatsu","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajay","family":"Mandlekar","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeannette","family":"Bohg","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref2","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","author":"Agrawal","journal-title":"Advances in Neural Information Processing Systems (NIPS), 2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.058"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref6","article-title":"Solving rubiks cube with a robot hand","author":"Akkaya","year":"1910","journal-title":"ArXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321799"},{"key":"ref8","article-title":"Teacher algorithms for curriculum learning of deep rl in continuously parameterized environments","volume-title":"Conference on Robot Learning","author":"Portelas"},{"key":"ref9","article-title":"Automated curriculum generation through setter-solver interactions","volume-title":"International Conference on Learning Representations (ICLR), 2020","author":"Racani\u00e8re"},{"key":"ref10","article-title":"Adaptive procedural task generation for hard-exploration problems","volume-title":"International Conference on Representation Learning (ICLR)","author":"Fang"},{"key":"ref11","first-page":"13049","article-title":"Emergent complexity and zero-shot transfer via unsupervised environment design","volume":"33","author":"Dennis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Prioritized level replay","author":"Jiang","year":"2010","journal-title":"ArXiv"},{"key":"ref13","article-title":"A simple neural network module for relational reasoning","author":"Santoro","journal-title":"Neural information processing systems, 2017"},{"key":"ref14","article-title":"Robonet: Large-scale multi-robot learning","volume-title":"Conference on Robot Learning","author":"Dasari"},{"key":"ref15","article-title":"RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation","volume-title":"Conference on Robot Learning, 2018","author":"Mandlekar"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968114"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref19","author":"Yu","year":"2020","journal-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning"},{"key":"ref20","article-title":"Dynamics learning with cascaded variational inference for multi-step manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Fang"},{"key":"ref21","article-title":"Surreal: Open-source reinforcement learning framework and robot manipulation benchmark","volume-title":"Conference on Robot Learning","author":"Fan"},{"key":"ref22","article-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale","volume-title":"Conference on Robot Learning (CoRL)","author":"Kalashnikov"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2846639"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0208-z"},{"key":"ref25","author":"Cobbe","year":"2020","journal-title":"Leveraging procedural generation to benchmark reinforcement learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562038"},{"key":"ref28","article-title":"Automatic synthesis of experiment designs from probabilistic environment specifications","volume-title":"Workshop on Synthesis (SYNT)","author":"Innes"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3133603"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00131"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00576"},{"key":"ref32","article-title":"Atiss: Autoregressive transformers for indoor scene synthesis","volume-title":"NeurIPS, 2021","author":"Paschalidou"},{"key":"ref33","article-title":"Active domain randomization","volume-title":"Conference on Robot Learning","author":"Mehta"},{"key":"ref34","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","volume-title":"International Conference on Learning Representations, 2018","author":"Sukhbaatar"},{"key":"ref35","article-title":"Learning goal embeddings via self-play for hierarchical reinforcement learning","author":"Sukhbaatar","year":"2018","journal-title":"CoRR"},{"key":"ref36","article-title":"Intrinsically motivated goal exploration processes with automatic curriculum learning","author":"Forestier","journal-title":"Journal of Machine Learning Research, 2022"},{"key":"ref37","article-title":"Automatic goal generation for reinforcement learning agents","volume-title":"International Conference on Machine Learning, 2018","author":"Held"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref39","first-page":"7648","article-title":"Automatic curriculum learning through value disagreement","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7416"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619131"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.010"},{"key":"ref43","article-title":"Enhanced poet: Open-ended reinforcement learning through unbounded invention of learning challenges and their solutions","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"ref45","article-title":"Evolving curricula with regret-based environment design","author":"Parker-Holder","journal-title":"ICML, 2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3476412"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.038"},{"key":"ref48","article-title":"Variational automatic curriculum learning for sparse-reward cooperative multi-agent problems","author":"Chen","journal-title":"Advances in Neural Information Processing Systems, 2021"},{"key":"ref49","article-title":"Curriculum reinforcement learning via constrained optimal transport","volume-title":"International Conference on Machine Learning","author":"Klink"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref51","article-title":"Hierarchical planning in the now","volume-title":"Workshops at the Twenty-Fourth AAAI Conference on Artificial Intelligence, 2010","author":"Kaelbling"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.044"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6739"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965875"},{"key":"ref55","article-title":"Learning parameterized skills","volume-title":"International Conference on Machine Learning, 2012","author":"Da Silva"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10226"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196958"},{"key":"ref58","article-title":"Adversarial skill chaining for long-horizon robot manipulation via terminal state regularization","volume-title":"5th Annual Conference on Robot Learning, 2021","author":"Lee"},{"key":"ref59","article-title":"Accelerating robotic reinforcement learning via parameterized action primitives","volume":"34","author":"Dalal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560841"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref62","first-page":"2661","article-title":"Zero-shot task generalization with multi-task deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Oh"},{"key":"ref63","article-title":"Regression planning networks","volume":"32","author":"Xu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560934"},{"key":"ref65","author":"McDermott","year":"1998","journal-title":"PDDL-The Planning Domain Definition Language Version 1.2"},{"key":"ref66","article-title":"Behavior from the void: Unsupervised active pre-training","author":"Liu","journal-title":"Neural Information Processing Systems, 2021"},{"key":"ref67","article-title":"Nonparametric entropy estimation: An overview","author":"Beirlant","journal-title":"International Journal of Mathematical and Statistical Sciences, 1997"},{"key":"ref68","article-title":"The nearest neighbor information estimator is adaptively near minimax rate-optimal","volume":"31","author":"Jiao","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812016"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"ref71","first-page":"2016","author":"Coumans","journal-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341727.pdf?arnumber=10341727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:17:00Z","timestamp":1703013420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341727\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341727","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}