{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:32:45Z","timestamp":1763191965954,"version":"3.45.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228697","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-Guided Curriculum Design: robust policy learning with adversarial environment"],"prefix":"10.1109","author":[{"given":"Wenning","family":"Hu","sequence":"first","affiliation":[{"name":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China"}]},{"given":"Lianke","family":"Zhou","sequence":"additional","affiliation":[{"name":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China"}]},{"given":"Ming","family":"He","sequence":"additional","affiliation":[{"name":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China"}]},{"given":"Nianbin","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China"}]}],"member":"263","reference":[{"article-title":"Playing atari with deep reinforcement learning[J]","year":"2013","author":"Mnih","key":"ref1"},{"key":"ref2","first-page":"24414","article-title":"Robust policy learning over multiple uncertainty sets[C]","volume-title":"International Conference on Machine Learning","author":"Xie"},{"journal-title":"Broadly-exploring, local-policy trees for long-horizon task planning[J]","year":"2020","author":"Ichter","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01289"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103923"},{"key":"ref7","first-page":"32868","article-title":"Grounding aleatoric uncertainty for unsupervised environment design[J]","volume":"35","author":"Jiang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","first-page":"13049","article-title":"Emergent complexity and zero-shot transfer via unsupervised environment design[J]","volume":"33","author":"Dennis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"4940","article-title":"Prioritized level replay[C]","volume-title":"International Conference on Machine Learning","author":"Jiang"},{"key":"ref10","first-page":"1884","article-title":"Replay-guided adversarial environment design[J]","volume":"34","author":"Jiang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","first-page":"29","article-title":"Deep exploration via bootstrapped DQN[J]","author":"Osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Sample efficient deep reinforcement learning via uncertainty estimation[J]","year":"2022","author":"Mai","key":"ref12"},{"key":"ref13","first-page":"15220","article-title":"How to stay curious while avoiding noisy tvs using aleatoric uncertainty estimation[C]","volume-title":"International Conference on Machine Learning","author":"Mavor-Parker"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3185159"},{"article-title":"Openai gym[J]","year":"2016","author":"Brockman","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref17","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents[C]","volume-title":"International conference on machine learning","author":"Florensa"},{"article-title":"Learning with amigo: Adversarially motivated intrinsic goals[J]","year":"2020","author":"Campero","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21959"},{"key":"ref20","first-page":"7648","article-title":"Automatic curriculum learning through value disagreement[J]","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","first-page":"16668","article-title":"Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills[C]","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934906"},{"key":"ref23","first-page":"30","article-title":"What uncertainties do we need in bayesian deep learning for computer vision?[J]","volume":"2017","author":"Kendall","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.4324\/9781315771946-5"},{"key":"ref25","first-page":"30","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles[J]","author":"Lakshminarayanan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"31","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models[J]","author":"Chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"11319","article-title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning[C]","volume-title":"International Conference on Machine Learning","author":"Wu"},{"article-title":"Episodic curiosity through reachability[J]","year":"2018","author":"Savinov","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228697.pdf?arnumber=11228697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:17Z","timestamp":1763191697000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228697","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}