{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T13:06:03Z","timestamp":1747400763956,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8460625","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"2425-2432","source":"Crossref","is-referenced-by-count":10,"title":["Online Learning of a Memory for Learning Rates"],"prefix":"10.1109","author":[{"given":"Franziska","family":"Meier","sequence":"first","affiliation":[]},{"given":"Daniel","family":"Kappler","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Schaal","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","author":"andrychowicz","year":"2016","journal-title":"Advances in neural information processing systems"},{"journal-title":"Learning to Optimize[J]","year":"2016","author":"li","key":"ref11"},{"key":"ref12","first-page":"1519","article-title":"Learning step size controllers for robust neural network training","author":"daniel","year":"2016","journal-title":"AAAI"},{"journal-title":"Using deep Q-learning to control optimization hyperparameters","year":"2016","author":"hansen","key":"ref13"},{"journal-title":"Deep q-networks for accelerating the training of deep neural networks","year":"2016","author":"fu","key":"ref14"},{"journal-title":"The MNIST Database of Handwritten Digits","year":"1998","author":"lecun","key":"ref15"},{"key":"ref16","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"arXiv e-prints 1703 03400"},{"key":"ref17","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2014","journal-title":"ArXiv e-prints"},{"key":"ref18","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref19","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","article-title":"Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning","author":"gu","year":"2017","journal-title":"ArXiv e-prints"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref3","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref6","article-title":"Learning to learn using gradient descent","author":"hochreiter","year":"2001","journal-title":"Proc Intl Conf on Artificial Neural Networks"},{"key":"ref5","article-title":"Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control","author":"kamthe","year":"2017","journal-title":"ArXiv e-prints"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00228-9"},{"key":"ref7","article-title":"Evolutionary principles in self-referential learning","author":"schmidhuber","year":"1987","journal-title":"On learning how to learn The meta-meta-… hook ) Diploma thesis Institut f Informatik Tech Univ Munich"},{"key":"ref2","article-title":"A new data source for inverse dynamics learning","author":"kappler","year":"2017","journal-title":"Proc IEEE\/RSJ Conf Intell Robots Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019956318069"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1126\/science.1253138","article-title":"A memory of errors in sensorimotor learning","author":"herzfeld","year":"2014","journal-title":"Science"},{"key":"ref20","article-title":"ADADELTA: An Adaptive Learning Rate Method","author":"zeiler","year":"2012","journal-title":"ArXiv e-prints"},{"key":"ref22","article-title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","author":"goyal","year":"2017","journal-title":"ArXiv e-prints"},{"key":"ref21","article-title":"SGDR: Stochastic Gradient Descent with Warm Restarts","author":"loshchilov","year":"2016","journal-title":"ArXiv e-prints"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298623"},{"key":"ref23","article-title":"Online Learning Rate Adaptation with Hypergradient Descent","author":"gunes baydin","year":"2017","journal-title":"ArXiv e-prints"},{"journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems","year":"2016","author":"abadi","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300016963"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2018,5,21]]},"location":"Brisbane, QLD","end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08460625.pdf?arnumber=8460625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:29:47Z","timestamp":1598232587000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8460625\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8460625","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}