{"list":"other","total":56,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"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":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"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":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1708.01547","title":"Lifelong Learning with Dynamically Expandable Networks","created":"2017-08-04","cited_by_count":694},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"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":"1611.06194","title":"Expert Gate: Lifelong Learning with a Network of Experts","created":"2016-11-18","cited_by_count":372},{"id":"1910.07104","title":"Orthogonal Gradient Descent for Continual Learning","created":"2019-10-15","cited_by_count":369},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"1708.02072","title":"Measuring Catastrophic Forgetting in Neural Networks","created":"2017-08-07","cited_by_count":360},{"id":"1904.00310","title":"Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting","created":"2019-03-31","cited_by_count":302},{"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":"1810.12488","title":"Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines","created":"2018-10-30","cited_by_count":228},{"id":"1910.02509","title":"REMIND Your Neural Network to Prevent Catastrophic Forgetting","created":"2019-10-06","cited_by_count":197},{"id":"1810.01256","title":"Continual Learning of Context-dependent Processing in Neural Networks","created":"2018-09-29","cited_by_count":179},{"id":"1510.09142","title":"Learning Continuous Control Policies by Stochastic Value Gradients","created":"2015-10-30","cited_by_count":162},{"id":"1805.09733","title":"Towards Robust Evaluations of Continual Learning","created":"2018-05-24","cited_by_count":148},{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143},{"id":"1809.05922","title":"Memory Efficient Experience Replay for Streaming Learning","created":"2018-09-16","cited_by_count":128},{"id":"1901.11356","title":"Functional Regularisation for Continual Learning with Gaussian Processes","created":"2019-01-31","cited_by_count":123},{"id":"2002.06487","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","created":"2020-02-16","cited_by_count":117},{"id":"1809.10635","title":"Generative replay with feedback connections as a general strategy for continual learning","created":"2018-09-27","cited_by_count":104},{"id":"1710.10368","title":"Deep Generative Dual Memory Network for Continual Learning","created":"2017-10-28","cited_by_count":59},{"id":"2007.07617","title":"SpaceNet: Make Free Space For Continual Learning","created":"2020-07-15","cited_by_count":53},{"id":"1705.09847","title":"Lifelong Generative Modeling","created":"2017-05-27","cited_by_count":51},{"id":"2203.10681","title":"Online Continual Learning for Embedded Devices","created":"2022-03-21","cited_by_count":49},{"id":"1812.02464","title":"Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting","created":"2018-12-06","cited_by_count":46},{"id":"1806.05421","title":"Selfless Sequential Learning","created":"2018-06-14","cited_by_count":44},{"id":"1902.00255","title":"Policy Consolidation for Continual Reinforcement Learning","created":"2019-02-01","cited_by_count":39},{"id":"2106.09835","title":"Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay","created":"2021-06-17","cited_by_count":31},{"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":"1903.03176","title":"MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments","created":"2019-03-07","cited_by_count":19},{"id":"2003.07417","title":"Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks","created":"2020-03-16","cited_by_count":17},{"id":"2007.09569","title":"Understanding and Mitigating the Limitations of Prioritized Experience Replay","created":"2020-07-19","cited_by_count":17},{"id":"2103.02886","title":"Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings","created":"2021-03-04","cited_by_count":12},{"id":"2002.05822","title":"Frequency-based Search-control in Dyna","created":"2020-02-14","cited_by_count":7},{"id":"1909.05106","title":"Correlation Priors for Reinforcement Learning","created":"2019-09-11","cited_by_count":3}],"next_cursor":null}