{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T06:00:17Z","timestamp":1759730417352,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650719","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["RLBOF: Reinforcement Learning from Bayesian Optimization Feedback"],"prefix":"10.1109","author":[{"given":"Hailong","family":"Huang","sequence":"first","affiliation":[{"name":"Zhejiang University,School of Sofware Technology,Ningbo,China"}]},{"given":"Xiubo","family":"Liang","sequence":"additional","affiliation":[{"name":"Zhejiang University,School of Sofware Technology,Ningbo,China"}]},{"given":"Quanwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University,School of Sofware Technology,Ningbo,China"}]},{"given":"Hongzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,School of Sofware Technology,Ningbo,China"}]},{"given":"Xiangdong","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-38527-2_55"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"article-title":"A tutorial on bayesian optimization","year":"2018","author":"Frazier","key":"ref3"},{"key":"ref4","article-title":"Practical bayesian optimization of machine learning algorithms","volume":"25","author":"Snoek","year":"2012","journal-title":"Advances in neural information processing systems"},{"article-title":"Effective surrogate models for protein design with bayesian optimization","volume-title":"ICML Workshop on Computational Biology","author":"Gruver","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3052391"},{"key":"ref7","first-page":"1378","article-title":"Hyperparameter transfer learning with adaptive complexity","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Horv\u00e1th"},{"key":"ref8","article-title":"Scalable hyperparameter transfer learning","volume":"31","author":"Perrone","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"2171","article-title":"Scalable bayesian optimization using deep neural networks","volume-title":"International conference on machine learning","author":"Snoek"},{"key":"ref10","article-title":"Bayesian optimization with robust bayesian neural networks","volume":"29","author":"Springenberg","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"11 058","article-title":"Meta-learning hyperparameter performance prediction with neural processes","volume-title":"International Conference on Machine Learning","author":"Wei"},{"article-title":"Transformer neural processes: Uncertainty-aware meta learning via sequence modeling","year":"2022","author":"Nguyen","key":"ref12"},{"article-title":"Meta-learning acquisition functions for transfer learning in bayesian optimization","year":"2019","author":"Volpp","key":"ref13"},{"key":"ref14","first-page":"7718","article-title":"Reinforced few-shot acquisition function learning for bayesian optimization","volume":"34","author":"Hsieh","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref16"},{"key":"ref17","first-page":"117","article-title":"The application of bayesian methods for seeking the extremum","volume":"2","author":"Mockus","year":"1998","journal-title":"Towards global optimization"},{"article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","year":"2009","author":"Srinivas","key":"ref18"},{"article-title":"A tutorial on bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning","year":"2010","author":"Brochu","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065704001899"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/S0927-0507(05)80172-0","article-title":"Markov decision processes","volume":"2","author":"Puterman","year":"1990","journal-title":"Handbooks in operations research and management science"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman"},{"key":"ref25","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proceedings of the Nineteenth International Conference on Machine Learning","author":"Kakade"},{"article-title":"Transfer learning for bayesian optimization: A survey","year":"2023","author":"Bai","key":"ref26"},{"article-title":"Meta-learning acquisition functions for transfer learning in bayesian optimization","year":"2019","author":"Volpp","key":"ref27"},{"key":"ref28","first-page":"199","article-title":"Collaborative hyperparameter tuning","volume-title":"International conference on machine learning","author":"Bardenet"},{"key":"ref29","article-title":"Scalable meta-learning for bayesian optimization using ranking-weighted gaussian process ensembles","volume-title":"AutoML Workshop at ICML","volume":"7","author":"Feurer"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098043"},{"article-title":"End-to-end learning of deep kernel acquisition functions for bayesian optimization","year":"2021","author":"Iwata","key":"ref31"},{"key":"ref32","first-page":"1704","article-title":"Conditional neural processes","volume-title":"International conference on machine learning","author":"Garnelo"},{"key":"ref33","first-page":"6606","article-title":"Boot-strapping neural processes","volume":"33","author":"Lee","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Attentive neural processes","year":"2019","author":"Kim","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Transformers can do bayesian inference","year":"2021","author":"M\u00fcller","key":"ref36"},{"article-title":"End-to-end meta-bayesian optimisation with transformer neural processes","year":"2023","author":"Maraval","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719857"},{"key":"ref39","article-title":"Gpytorch: Blackbox matrix-matrix gaussian process inference with gpu acceleration","volume":"31","author":"Gardner","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21105\/joss.05320"},{"article-title":"Benchmark functions for bayesian optimization","year":"2020","author":"Kim","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-017-5684-y"},{"article-title":"Palr: Personalization aware llms for recommendation","year":"2023","author":"Chen","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608860"},{"article-title":"Do llms understand user preferences? evaluating llms on user rating prediction","year":"2023","author":"Kang","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-023-03172-7"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650719.pdf?arnumber=10650719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:59:46Z","timestamp":1725947986000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650719","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}