{"list":"other","total":62,"rows":[{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"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":"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":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"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":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1611.04558","title":"Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation","created":"2016-11-14","cited_by_count":469},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"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":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"1901.11504","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","created":"2019-01-31","cited_by_count":350},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"1703.07326","title":"One-Shot Imitation Learning","created":"2017-03-21","cited_by_count":233},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"1812.00568","title":"Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control","created":"2018-12-03","cited_by_count":230},{"id":"1709.04905","title":"One-Shot Visual Imitation Learning via Meta-Learning","created":"2017-09-14","cited_by_count":228},{"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":"1509.06825","title":"Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours","created":"2015-09-23","cited_by_count":209},{"id":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"1802.10567","title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","created":"2018-02-28","cited_by_count":167},{"id":"1802.01557","title":"One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning","created":"2018-02-05","cited_by_count":148},{"id":"2003.13661","title":"Multi-Task Reinforcement Learning with Soft Modularization","created":"2020-03-30","cited_by_count":143},{"id":"1809.04474","title":"Multi-task Deep Reinforcement Learning with PopArt","created":"2018-09-12","cited_by_count":141},{"id":"1802.07245","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","created":"2018-02-20","cited_by_count":130},{"id":"1803.09956","title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","created":"2018-03-27","cited_by_count":128},{"id":"1802.02950","title":"Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting","created":"2018-02-08","cited_by_count":127},{"id":"1707.02920","title":"Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration","created":"2017-07-10","cited_by_count":100},{"id":"1810.06784","title":"ProMP: Proximal Meta-Policy Search","created":"2018-10-16","cited_by_count":91},{"id":"1802.04821","title":"Evolved Policy Gradients","created":"2018-02-13","cited_by_count":88},{"id":"1712.07294","title":"Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning","created":"2017-12-20","cited_by_count":77},{"id":"1905.03030","title":"Meta-learning of Sequential Strategies","created":"2019-05-08","cited_by_count":70},{"id":"1810.03237","title":"Task-Embedded Control Networks for Few-Shot Imitation Learning","created":"2018-10-08","cited_by_count":66},{"id":"1705.10479","title":"Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets","created":"2017-05-30","cited_by_count":64},{"id":"2002.11089","title":"Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement","created":"2020-02-25","cited_by_count":60},{"id":"1710.10368","title":"Deep Generative Dual Memory Network for Continual Learning","created":"2017-10-28","cited_by_count":59},{"id":"1804.00079","title":"Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning","created":"2018-03-30","cited_by_count":52},{"id":"1711.09874","title":"Divide-and-Conquer Reinforcement Learning","created":"2017-11-27","cited_by_count":48},{"id":"1904.11455","title":"Ray Interference: a Source of Plateaus in Deep Reinforcement Learning","created":"2019-04-25","cited_by_count":40},{"id":"1604.01360","title":"The Curious Robot: Learning Visual Representations via Physical Interactions","created":"2016-04-05","cited_by_count":38},{"id":"1609.09025","title":"Learning to Push by Grasping: Using multiple tasks for effective learning","created":"2016-09-28","cited_by_count":37},{"id":"1904.05538","title":"Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight","created":"2019-04-11","cited_by_count":34},{"id":"1810.11043","title":"One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks","created":"2018-10-25","cited_by_count":33},{"id":"1911.01103","title":"Learning One-Shot Imitation from Humans without Humans","created":"2019-11-04","cited_by_count":33},{"id":"1904.00956","title":"Guided Meta-Policy Search","created":"2019-04-01","cited_by_count":26},{"id":"2002.09093","title":"The Surprising Effectiveness of Linear Models for Visual Foresight in Object Pile Manipulation","created":"2020-02-21","cited_by_count":25},{"id":"1911.05071","title":"Experience-Embedded Visual Foresight","created":"2019-11-12","cited_by_count":21},{"id":"2003.02636","title":"Scalable Multi-Task Imitation Learning with Autonomous Improvement","created":"2020-02-25","cited_by_count":21},{"id":"2002.09107","title":"Learning Precise 3D Manipulation from Multiple Uncalibrated Cameras","created":"2020-02-21","cited_by_count":18},{"id":"1802.01034","title":"Multi-task Learning for Continuous Control","created":"2018-02-03","cited_by_count":6}],"next_cursor":null}