{"list":"other","total":51,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1801.10112","title":"Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence","created":"2018-01-30","cited_by_count":742},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1904.07734","title":"Three scenarios for continual learning","created":"2019-04-15","cited_by_count":614},{"id":"1903.08671","title":"Gradient based sample selection for online continual learning","created":"2019-03-20","cited_by_count":571},{"id":"1810.11910","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","created":"2018-10-29","cited_by_count":521},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"1908.04742","title":"Online Continual Learning with Maximally Interfered Retrieval","created":"2019-08-11","cited_by_count":379},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1710.10628","title":"Variational Continual Learning","created":"2017-10-29","cited_by_count":339},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1802.10269","title":"Selective Experience Replay for Lifelong Learning","created":"2018-02-28","cited_by_count":241},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"1805.09733","title":"Towards Robust Evaluations of Continual Learning","created":"2018-05-24","cited_by_count":148},{"id":"1905.11614","title":"Uncertainty-based Continual Learning with Adaptive Regularization","created":"2019-05-28","cited_by_count":146},{"id":"2001.00689","title":"A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning","created":"2020-01-03","cited_by_count":134},{"id":"1901.11356","title":"Functional Regularisation for Continual Learning with Gaussian Processes","created":"2019-01-31","cited_by_count":123},{"id":"2004.14070","title":"Continual Deep Learning by Functional Regularisation of Memorable Past","created":"2020-04-29","cited_by_count":105},{"id":"1805.08289","title":"Measuring and regularizing networks in function space","created":"2018-05-21","cited_by_count":99},{"id":"2012.12631","title":"Efficient Continual Learning with Modular Networks and Task-Driven Priors","created":"2020-12-23","cited_by_count":88},{"id":"1803.07055","title":"Simple random search provides a competitive approach to reinforcement learning","created":"2018-03-19","cited_by_count":75},{"id":"2007.05549","title":"Meta-Learning Requires Meta-Augmentation","created":"2020-07-10","cited_by_count":57},{"id":"2002.02693","title":"Ready Policy One: World Building Through Active Learning","created":"2020-02-07","cited_by_count":33},{"id":"2103.03216","title":"Continuous Coordination As a Realistic Scenario for Lifelong Learning","created":"2021-03-04","cited_by_count":32},{"id":"1906.10667","title":"Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives","created":"2019-06-25","cited_by_count":30},{"id":"2007.07011","title":"Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting","created":"2020-07-14","cited_by_count":29},{"id":"1910.01913","title":"If MaxEnt RL is the Answer, What is the Question?","created":"2019-10-04","cited_by_count":27},{"id":"2010.02418","title":"The Effectiveness of Memory Replay in Large Scale Continual Learning","created":"2020-10-06","cited_by_count":26},{"id":"1912.02290","title":"Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning","created":"2019-12-04","cited_by_count":11}],"next_cursor":null}