{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1801.10112","title":"Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence","created":"2018-01-30","cited_by_count":742},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"1904.07734","title":"Three scenarios for continual learning","created":"2019-04-15","cited_by_count":614},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1908.04742","title":"Online Continual Learning with Maximally Interfered Retrieval","created":"2019-08-11","cited_by_count":379},{"id":"1902.10486","title":"On Tiny Episodic Memories in Continual Learning","created":"2019-02-27","cited_by_count":307},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"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":"1812.02648","title":"Deep Reinforcement Learning and the Deadly Triad","created":"2018-12-06","cited_by_count":174},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"2003.13661","title":"Multi-Task Reinforcement Learning with Soft Modularization","created":"2020-03-30","cited_by_count":143},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116},{"id":"1812.07671","title":"Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL","created":"2018-12-18","cited_by_count":81},{"id":"1512.04455","title":"Memory-based control with recurrent neural networks","created":"2015-12-14","cited_by_count":78},{"id":"2003.07305","title":"DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction","created":"2020-03-16","cited_by_count":71},{"id":"1308.3513","title":"Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations","created":"2013-08-15","cited_by_count":70},{"id":"1910.00125","title":"Meta-Q-Learning","created":"2019-09-30","cited_by_count":62},{"id":"1803.10123","title":"Task Agnostic Continual Learning Using Online Variational Bayes","created":"2018-03-27","cited_by_count":61},{"id":"1906.05201","title":"Task Agnostic Continual Learning via Meta Learning","created":"2019-06-12","cited_by_count":53},{"id":"2006.10701","title":"Deep Reinforcement Learning amidst Lifelong Non-Stationarity","created":"2020-06-18","cited_by_count":43},{"id":"2106.02940","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","created":"2021-06-05","cited_by_count":43},{"id":"2104.01678","title":"Understanding Continual Learning Settings with Data Distribution Drift Analysis","created":"2021-04-04","cited_by_count":38},{"id":"1905.01756","title":"P3O: Policy-on Policy-off Policy Optimization","created":"2019-05-05","cited_by_count":37},{"id":"1907.05855","title":"DisCoRL: Continual Reinforcement Learning via Policy Distillation","created":"2019-07-11","cited_by_count":36},{"id":"2103.07492","title":"Continual Learning for Recurrent Neural Networks: an Empirical Evaluation","created":"2021-03-12","cited_by_count":34},{"id":"1802.07239","title":"Continual Reinforcement Learning with Complex Synapses","created":"2018-02-20","cited_by_count":32},{"id":"1912.03049","title":"Regularization Shortcomings for Continual Learning","created":"2019-12-06","cited_by_count":32},{"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":"2006.11441","title":"Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes","created":"2020-06-19","cited_by_count":23},{"id":"2108.01005","title":"Sequoia: A Software Framework to Unify Continual Learning Research","created":"2021-08-02","cited_by_count":19},{"id":"2007.00487","title":"Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes","created":"2020-07-01","cited_by_count":17},{"id":"2112.04467","title":"CoMPS: Continual Meta Policy Search","created":"2021-12-08","cited_by_count":15},{"id":"1906.00654","title":"Continual Learning of New Sound Classes using Generative Replay","created":"2019-06-03","cited_by_count":11},{"id":"2004.07530","title":"Continual Reinforcement Learning with Multi-Timescale Replay","created":"2020-04-16","cited_by_count":10},{"id":"1909.10008","title":"Multi-task Learning and Catastrophic Forgetting in Continual Reinforcement Learning","created":"2019-09-22","cited_by_count":5},{"id":"1905.02662","title":"Continual and Multi-task Reinforcement Learning With Shared Episodic Memory","created":"2019-05-07","cited_by_count":3},{"id":"1805.05758","title":"Continuous Learning in a Hierarchical Multiscale Neural Network","created":"2018-05-15","cited_by_count":2}],"next_cursor":null}