Machine LearningPub Date : 2025-12-28DOI: 10.1007/s10994-025-06929-4
Hao Ma, Melanie N. Zeilinger, Michael Muehlebach
{"title":"Stochastic Online Optimization for Cyber-Physical and Robotic Systems","authors":"Hao Ma, Melanie N. Zeilinger, Michael Muehlebach","doi":"10.1007/s10994-025-06929-4","DOIUrl":"https://doi.org/10.1007/s10994-025-06929-4","url":null,"abstract":"Abstract We propose a gradient-based online optimization framework for solving stochastic programming problems that frequently arise in the context of cyber-physical and robotic systems. Our problem formulation accommodates constraints that model the evolution of a cyber-physical system, which has, in general, a continuous state and action space, is nonlinear, and where the state is only partially observed. We also incorporate an approximate model of the dynamics as prior knowledge into the learning process and show that even rough estimates of the dynamics can significantly improve the convergence of our algorithms. Our online optimization framework encompasses both gradient descent and quasi-Newton methods, and we provide a unified convergence analysis of our algorithms in a non-convex setting. We also characterize the impact of modeling errors in the system dynamics on the convergence rate of the algorithms. Finally, we evaluate our algorithms in simulations of a flexible beam, a four-legged walking robot, and in real-world experiments with a ping-pong playing robot.","PeriodicalId":506175,"journal":{"name":"Machine Learning","volume":"115 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10994-025-06929-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147903439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Machine LearningPub Date : 2024-07-15DOI: 10.1007/s10994-024-06592-1
Tuan T. Nguyen, Hoang H. Nguyen, Mina Sartipi, Marco Fisichella
{"title":"LaMMOn: language model combined graph neural network for multi-target multi-camera tracking in online scenarios","authors":"Tuan T. Nguyen, Hoang H. Nguyen, Mina Sartipi, Marco Fisichella","doi":"10.1007/s10994-024-06592-1","DOIUrl":"https://doi.org/10.1007/s10994-024-06592-1","url":null,"abstract":"","PeriodicalId":506175,"journal":{"name":"Machine Learning","volume":"43 43","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141645233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Machine LearningPub Date : 2024-06-10DOI: 10.1007/s10994-024-06563-6
Michał Koziarski, Michał Woźniak
{"title":"Local neighborhood encodings for imbalanced data classification","authors":"Michał Koziarski, Michał Woźniak","doi":"10.1007/s10994-024-06563-6","DOIUrl":"https://doi.org/10.1007/s10994-024-06563-6","url":null,"abstract":"","PeriodicalId":506175,"journal":{"name":"Machine Learning","volume":"105 14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141362111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Machine LearningPub Date : 2024-06-05DOI: 10.1007/s10994-024-06547-6
Keita Ota, Devesh K. Jha, Asako Kanezaki
{"title":"A framework for training larger networks for deep Reinforcement learning","authors":"Keita Ota, Devesh K. Jha, Asako Kanezaki","doi":"10.1007/s10994-024-06547-6","DOIUrl":"https://doi.org/10.1007/s10994-024-06547-6","url":null,"abstract":"","PeriodicalId":506175,"journal":{"name":"Machine Learning","volume":"314 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141386180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Machine LearningPub Date : 2024-02-23DOI: 10.1007/s10994-024-06514-1
Vincent Mai, Philippe Maisonneuve, Tianyu Zhang, Hadi Nekoei, Liam Paull, Antoine Lesage-Landry
{"title":"Correction to: Multi-agent reinforcement learning for fast-timescale demand response of residential loads","authors":"Vincent Mai, Philippe Maisonneuve, Tianyu Zhang, Hadi Nekoei, Liam Paull, Antoine Lesage-Landry","doi":"10.1007/s10994-024-06514-1","DOIUrl":"https://doi.org/10.1007/s10994-024-06514-1","url":null,"abstract":"","PeriodicalId":506175,"journal":{"name":"Machine Learning","volume":"29 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140435621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}