{"list":"other","total":57,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"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":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1909.05207","title":"Introduction to Online Convex Optimization","created":"2019-09-07","cited_by_count":803},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"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":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"id":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"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":"1810.03548","title":"Meta-Learning: A Survey","created":"2018-10-08","cited_by_count":256},{"id":"1511.05641","title":"Net2Net: Accelerating Learning via Knowledge Transfer","created":"2015-11-18","cited_by_count":250},{"id":"1802.10269","title":"Selective Experience Replay for Lifelong Learning","created":"2018-02-28","cited_by_count":241},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"1812.03596","title":"Task-Free Continual Learning","created":"2018-12-10","cited_by_count":221},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"1905.12588","title":"Meta-Learning Representations for Continual Learning","created":"2019-05-29","cited_by_count":189},{"id":"1906.02717","title":"Adaptive Gradient-Based Meta-Learning Methods","created":"2019-06-06","cited_by_count":183},{"id":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"1902.00164","title":"DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension","created":"2019-02-01","cited_by_count":156},{"id":"1802.01557","title":"One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning","created":"2018-02-05","cited_by_count":148},{"id":"1802.07245","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","created":"2018-02-20","cited_by_count":130},{"id":"1710.03641","title":"Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments","created":"2017-10-10","cited_by_count":108},{"id":"2008.06043","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","created":"2020-08-13","cited_by_count":93},{"id":"1810.06784","title":"ProMP: Proximal Meta-Policy Search","created":"2018-10-16","cited_by_count":91},{"id":"1604.07255","title":"A Deep Hierarchical Approach to Lifelong Learning in Minecraft","created":"2016-04-25","cited_by_count":90},{"id":"1802.04821","title":"Evolved Policy Gradients","created":"2018-02-13","cited_by_count":88},{"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":"1710.11622","title":"Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm","created":"2017-10-31","cited_by_count":65},{"id":"1906.05374","title":"Meta-Learning via Learned Loss","created":"2019-06-12","cited_by_count":60},{"id":"1906.05201","title":"Task Agnostic Continual Learning via Meta Learning","created":"2019-06-12","cited_by_count":53},{"id":"2007.13904","title":"La-MAML: Look-ahead Meta Learning for Continual Learning","created":"2020-07-27","cited_by_count":52},{"id":"1912.08866","title":"Continuous Meta-Learning without Tasks","created":"2019-12-18","cited_by_count":50},{"id":"1611.01843","title":"Learning to Perform Physics Experiments via Deep Reinforcement Learning","created":"2016-11-06","cited_by_count":47},{"id":"1812.02464","title":"Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting","created":"2018-12-06","cited_by_count":46},{"id":"1803.01118","title":"Some Considerations on Learning to Explore via Meta-Reinforcement Learning","created":"2018-03-03","cited_by_count":44},{"id":"1803.07551","title":"Meta Reinforcement Learning with Latent Variable Gaussian Processes","created":"2018-03-20","cited_by_count":44},{"id":"2010.00352","title":"Meta-Consolidation for Continual Learning","created":"2020-10-01","cited_by_count":40},{"id":"1806.04640","title":"Unsupervised Meta-Learning for Reinforcement Learning","created":"2018-06-12","cited_by_count":39},{"id":"1706.09529","title":"Learning to Learn: Meta-Critic Networks for Sample Efficient Learning","created":"2017-06-29","cited_by_count":28},{"id":"2010.11545","title":"Online Structured Meta-learning","created":"2020-10-22","cited_by_count":27},{"id":"1904.00956","title":"Guided Meta-Policy Search","created":"2019-04-01","cited_by_count":26},{"id":"2004.11967","title":"Defining Benchmarks for Continual Few-Shot Learning","created":"2020-04-15","cited_by_count":21},{"id":"1802.04765","title":"Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control","created":"2018-02-13","cited_by_count":14},{"id":"2008.02598","title":"Offline Meta Learning of Exploration","created":"2020-08-06","cited_by_count":13},{"id":"2012.07769","title":"Variable-Shot Adaptation for Online Meta-Learning","created":"2020-12-14","cited_by_count":2}],"next_cursor":null}