{"list":"other","total":65,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1911.09785","title":"ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring","created":"2019-11-21","cited_by_count":349},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"1710.06542","title":"Asymmetric Actor Critic for Image-Based Robot Learning","created":"2017-10-18","cited_by_count":238},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"1910.02190","title":"Kornia: an Open Source Differentiable Computer Vision Library for PyTorch","created":"2019-10-05","cited_by_count":232},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"2012.02924","title":"iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes","created":"2020-12-05","cited_by_count":155},{"id":"1711.00138","title":"Visualizing and Understanding Atari Agents","created":"2017-10-31","cited_by_count":141},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"2007.04309","title":"Self-Supervised Policy Adaptation during Deployment","created":"2020-07-08","cited_by_count":123},{"id":"1810.00123","title":"Generalization and Regularization in DQN","created":"2018-09-29","cited_by_count":118},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"1910.12911","title":"Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck","created":"2019-10-28","cited_by_count":101},{"id":"1805.11592","title":"Playing hard exploration games by watching YouTube","created":"2018-05-29","cited_by_count":99},{"id":"1807.01697","title":"Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations","created":"2018-07-04","cited_by_count":99},{"id":"1912.02975","title":"Observational Overfitting in Reinforcement Learning","created":"2019-12-06","cited_by_count":91},{"id":"2006.09001","title":"RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real","created":"2020-06-16","cited_by_count":91},{"id":"1910.14442","title":"Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environments","created":"2019-10-30","cited_by_count":90},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"id":"1902.02186","title":"Distilling Policy Distillation","created":"2019-02-06","cited_by_count":84},{"id":"1806.10729","title":"Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation","created":"2018-06-28","cited_by_count":81},{"id":"2010.10814","title":"Improving Generalization in Reinforcement Learning with Mixture Regularization","created":"2020-10-21","cited_by_count":81},{"id":"1807.07049","title":"Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias","created":"2018-07-18","cited_by_count":75},{"id":"2006.12862","title":"Automatic Data Augmentation for Generalization in Deep Reinforcement Learning","created":"2020-06-23","cited_by_count":71},{"id":"1703.02660","title":"Towards Generalization and Simplicity in Continuous Control","created":"2017-03-08","cited_by_count":68},{"id":"1806.07377","title":"Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation","created":"2018-05-31","cited_by_count":50},{"id":"1905.12654","title":"On the Generalization Gap in Reparameterizable Reinforcement Learning","created":"2019-05-29","cited_by_count":22},{"id":"1910.07719","title":"Single Episode Policy Transfer in Reinforcement Learning","created":"2019-10-17","cited_by_count":18},{"id":"2008.11911","title":"Domain Adaptation Through Task Distillation","created":"2020-08-27","cited_by_count":11},{"id":"1802.01034","title":"Multi-task Learning for Continuous Control","created":"2018-02-03","cited_by_count":6}],"next_cursor":null}