{"list":"other","total":91,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1805.10965","title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation","created":"2018-05-28","cited_by_count":415},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1709.10190","title":"Unified Deep Supervised Domain Adaptation and Generalization","created":"2017-09-28","cited_by_count":323},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"1906.04893","title":"Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks","created":"2019-06-12","cited_by_count":293},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1901.09005","title":"Revisiting Self-Supervised Visual Representation Learning","created":"2019-01-25","cited_by_count":251},{"id":"1909.00889","title":"Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data","created":"2019-09-02","cited_by_count":246},{"id":"1710.06542","title":"Asymmetric Actor Critic for Image-Based Robot Learning","created":"2017-10-18","cited_by_count":238},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237},{"id":"1907.00953","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","created":"2019-07-01","cited_by_count":231},{"id":"2303.18240","title":"Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?","created":"2023-03-31","cited_by_count":218},{"id":"1810.05687","title":"Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience","created":"2018-10-12","cited_by_count":217},{"id":"1402.0555","title":"Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits","created":"2014-02-04","cited_by_count":201},{"id":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"1901.09184","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","created":"2019-01-26","cited_by_count":174},{"id":"1510.09142","title":"Learning Continuous Control Policies by Stochastic Value Gradients","created":"2015-10-30","cited_by_count":162},{"id":"1806.09460","title":"A Tour of Reinforcement Learning: The View from Continuous Control","created":"2018-06-25","cited_by_count":151},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"1812.05069","title":"Recent Advances in Autoencoder-Based Representation Learning","created":"2018-12-12","cited_by_count":133},{"id":"2007.04309","title":"Self-Supervised Policy Adaptation during Deployment","created":"2020-07-08","cited_by_count":123},{"id":"1905.05824","title":"Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models","created":"2019-05-14","cited_by_count":117},{"id":"2001.09576","title":"Naive Exploration is Optimal for Online LQR","created":"2020-01-27","cited_by_count":116},{"id":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"2101.02722","title":"The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels","created":"2021-01-07","cited_by_count":100},{"id":"2105.05837","title":"When Does Contrastive Visual Representation Learning Work?","created":"2021-05-12","cited_by_count":92},{"id":"1912.02975","title":"Observational Overfitting in Reinforcement Learning","created":"2019-12-06","cited_by_count":91},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"id":"2202.08345","title":"Learning Smooth Neural Functions via Lipschitz Regularization","created":"2022-02-16","cited_by_count":86},{"id":"1805.08498","title":"Implicit Reparameterization Gradients","created":"2018-05-22","cited_by_count":85},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"2212.08860","title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning","created":"2022-12-17","cited_by_count":60},{"id":"2012.02788","title":"Neural Dynamic Policies for End-to-End Sensorimotor Learning","created":"2020-12-04","cited_by_count":58},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57},{"id":"1904.10729","title":"Neural Logic Reinforcement Learning","created":"2019-04-24","cited_by_count":53},{"id":"2306.01439","title":"Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction","created":"2023-06-02","cited_by_count":46},{"id":"2210.07241","title":"Visual Reinforcement Learning with Self-Supervised 3D Representations","created":"2022-10-13","cited_by_count":45},{"id":"2302.04449","title":"Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals","created":"2023-02-09","cited_by_count":45},{"id":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43},{"id":"1809.10330","title":"Variance reduction properties of the reparameterization trick","created":"2018-09-27","cited_by_count":41},{"id":"2110.14770","title":"TRAIL: Near-Optimal Imitation Learning with Suboptimal Data","created":"2021-10-27","cited_by_count":39},{"id":"1905.08188","title":"A Bayesian Approach to Robust Reinforcement Learning","created":"2019-05-20","cited_by_count":34},{"id":"2209.09203","title":"Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning","created":"2022-09-16","cited_by_count":34},{"id":"1610.02287","title":"The Generalized Reparameterization Gradient","created":"2016-10-07","cited_by_count":30},{"id":"2104.02921","title":"Unsupervised Visual Attention and Invariance for Reinforcement Learning","created":"2021-04-07","cited_by_count":30},{"id":"1801.03326","title":"Expected Policy Gradients for Reinforcement Learning","created":"2018-01-10","cited_by_count":28},{"id":"2203.00543","title":"On the Generalization of Representations in Reinforcement Learning","created":"2022-03-01","cited_by_count":28},{"id":"2001.05411","title":"Lipschitz Lifelong Reinforcement Learning","created":"2020-01-15","cited_by_count":23},{"id":"1905.12654","title":"On the Generalization Gap in Reparameterizable Reinforcement Learning","created":"2019-05-29","cited_by_count":22},{"id":"1912.09588","title":"Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax","created":"2019-12-19","cited_by_count":18},{"id":"2011.01089","title":"Instance based Generalization in Reinforcement Learning","created":"2020-11-02","cited_by_count":17},{"id":"2004.14309","title":"How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization","created":"2020-04-29","cited_by_count":16},{"id":"2111.06888","title":"Learning Generalized Gumbel-max Causal Mechanisms","created":"2021-11-11","cited_by_count":16},{"id":"2205.02886","title":"Data Augmentation for Manipulation","created":"2022-05-05","cited_by_count":16},{"id":"2205.13728","title":"GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis","created":"2022-05-27","cited_by_count":16},{"id":"2207.02357","title":"Instance-optimal PAC Algorithms for Contextual Bandits","created":"2022-07-05","cited_by_count":16},{"id":"1810.09656","title":"Hierarchical Approaches for Reinforcement Learning in Parameterized Action Space","created":"2018-10-23","cited_by_count":15},{"id":"2101.11046","title":"Generalized Doubly Reparameterized Gradient Estimators","created":"2021-01-26","cited_by_count":14},{"id":"1908.03627","title":"Vision-based Navigation Using Deep Reinforcement Learning","created":"2019-08-08","cited_by_count":13},{"id":"2302.06548","title":"Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning","created":"2023-02-13","cited_by_count":13},{"id":"2306.00656","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","created":"2023-06-01","cited_by_count":13},{"id":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12},{"id":"1912.08324","title":"Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation","created":"2019-12-18","cited_by_count":9},{"id":"2212.14849","title":"Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search","created":"2022-12-30","cited_by_count":9}],"next_cursor":null}