{"list":"other","total":58,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"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":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"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":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1907.07484","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","created":"2019-07-17","cited_by_count":336},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"1506.07365","title":"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images","created":"2015-06-24","cited_by_count":274},{"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":"1711.00848","title":"Variational Inference of Disentangled Latent Concepts from Unlabeled Observations","created":"2017-11-02","cited_by_count":241},{"id":"2002.02886","title":"Weakly-Supervised Disentanglement Without Compromises","created":"2020-02-07","cited_by_count":239},{"id":"1805.12177","title":"Why do deep convolutional networks generalize so poorly to small image transformations?","created":"2018-05-30","cited_by_count":198},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"1812.07252","title":"Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks","created":"2018-12-18","cited_by_count":174},{"id":"1812.11103","title":"Learning to Walk via Deep Reinforcement Learning","created":"2018-12-26","cited_by_count":158},{"id":"1509.06113","title":"Deep Spatial Autoencoders for Visuomotor Learning","created":"2015-09-21","cited_by_count":153},{"id":"1707.08475","title":"DARLA: Improving Zero-Shot Transfer in Reinforcement Learning","created":"2017-07-26","cited_by_count":149},{"id":"1905.13662","title":"On the Fairness of Disentangled Representations","created":"2019-05-31","cited_by_count":144},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"1904.07854","title":"End-to-End Robotic Reinforcement Learning without Reward Engineering","created":"2019-04-16","cited_by_count":122},{"id":"1503.03167","title":"Deep Convolutional Inverse Graphics Network","created":"2015-03-11","cited_by_count":121},{"id":"2010.04296","title":"CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning","created":"2020-10-08","cited_by_count":109},{"id":"2004.09124","title":"Compositionality and Generalization in Emergent Languages","created":"2020-04-20","cited_by_count":103},{"id":"1802.05312","title":"Learning Deep Disentangled Embeddings with the F-Statistic Loss","created":"2018-02-14","cited_by_count":101},{"id":"1905.12506","title":"Are Disentangled Representations Helpful for Abstract Visual Reasoning?","created":"2019-05-29","cited_by_count":100},{"id":"1906.03292","title":"On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset","created":"2019-06-07","cited_by_count":100},{"id":"2007.08558","title":"On Robustness and Transferability of Convolutional Neural Networks","created":"2020-07-16","cited_by_count":98},{"id":"1610.04286","title":"Sim-to-Real Robot Learning from Pixels with Progressive Nets","created":"2016-10-13","cited_by_count":94},{"id":"2006.07886","title":"On Disentangled Representations Learned From Correlated Data","created":"2020-06-14","cited_by_count":94},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81},{"id":"2010.14407","title":"On the Transfer of Disentangled Representations in Realistic Settings","created":"2020-10-27","cited_by_count":63},{"id":"1804.02086","title":"Structured Disentangled Representations","created":"2018-04-06","cited_by_count":62},{"id":"2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","created":"2021-07-02","cited_by_count":53},{"id":"1807.10108","title":"Effects of Degradations on Deep Neural Network Architectures","created":"2018-07-26","cited_by_count":48},{"id":"1703.00727","title":"Deep Predictive Policy Training using Reinforcement Learning","created":"2017-03-02","cited_by_count":32},{"id":"2008.03596","title":"TriFinger: An Open-Source Robot for Learning Dexterity","created":"2020-08-08","cited_by_count":31},{"id":"1811.04784","title":"Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representations","created":"2018-11-12","cited_by_count":28},{"id":"1612.00429","title":"Generalizing Skills with Semi-Supervised Reinforcement Learning","created":"2016-12-01","cited_by_count":18},{"id":"2105.02087","title":"Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation","created":"2021-05-05","cited_by_count":15},{"id":"1810.11776","title":"Learning stable and predictive structures in kinetic systems: Benefits of a causal approach","created":"2018-10-28","cited_by_count":12},{"id":"2011.01758","title":"Representation Matters: Improving Perception and Exploration for Robotics","created":"2020-11-03","cited_by_count":11},{"id":"2012.09126","title":"Planning from Pixels in Atari with Learned Symbolic Representations","created":"2020-12-16","cited_by_count":11},{"id":"2002.05518","title":"Learning State Abstractions for Transfer in Continuous Control","created":"2020-02-08","cited_by_count":3}],"next_cursor":null}