{"list":"other","total":56,"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":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"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":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1904.06991","title":"Improved Precision and Recall Metric for Assessing Generative Models","created":"2019-04-15","cited_by_count":944},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1806.00035","title":"Assessing Generative Models via Precision and Recall","created":"2018-05-31","cited_by_count":406},{"id":"1610.00633","title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","created":"2016-10-03","cited_by_count":353},{"id":"1603.02199","title":"Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection","created":"2016-03-07","cited_by_count":316},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"1711.00848","title":"Variational Inference of Disentangled Latent Concepts from Unlabeled Observations","created":"2017-11-02","cited_by_count":241},{"id":"1710.06542","title":"Asymmetric Actor Critic for Image-Based Robot Learning","created":"2017-10-18","cited_by_count":238},{"id":"1509.06113","title":"Deep Spatial Autoencoders for Visuomotor Learning","created":"2015-09-21","cited_by_count":153},{"id":"1802.01557","title":"One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning","created":"2018-02-05","cited_by_count":148},{"id":"2011.10024","title":"Parrot: Data-Driven Behavioral Priors for Reinforcement Learning","created":"2020-11-19","cited_by_count":138},{"id":"1812.05069","title":"Recent Advances in Autoencoder-Based Representation Learning","created":"2018-12-12","cited_by_count":133},{"id":"2011.07213","title":"PLAS: Latent Action Space for Offline Reinforcement Learning","created":"2020-11-14","cited_by_count":133},{"id":"1806.02426","title":"Deep Variational Reinforcement Learning for POMDPs","created":"2018-06-06","cited_by_count":125},{"id":"1810.06544","title":"Deep Imitative Models for Flexible Inference, Planning, and Control","created":"2018-10-15","cited_by_count":76},{"id":"1803.06773","title":"Composable Deep Reinforcement Learning for Robotic Manipulation","created":"2018-03-19","cited_by_count":72},{"id":"2012.02788","title":"Neural Dynamic Policies for End-to-End Sensorimotor Learning","created":"2020-12-04","cited_by_count":58},{"id":"2005.07513","title":"A Distributional View on Multi-Objective Policy Optimization","created":"2020-05-15","cited_by_count":52},{"id":"1708.04225","title":"Deep Object-Centric Representations for Generalizable Robot Learning","created":"2017-08-14","cited_by_count":50},{"id":"1909.12906","title":"Meta Reinforcement Learning for Sim-to-real Domain Adaptation","created":"2019-09-16","cited_by_count":49},{"id":"1802.03006","title":"Learning and Querying Fast Generative Models for Reinforcement Learning","created":"2018-02-08","cited_by_count":48},{"id":"1802.10264","title":"Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods","created":"2018-02-28","cited_by_count":33},{"id":"1703.00727","title":"Deep Predictive Policy Training using Reinforcement Learning","created":"2017-03-02","cited_by_count":32},{"id":"1511.07111","title":"Adapting Deep Visuomotor Representations with Weak Pairwise Constraints","created":"2015-11-23","cited_by_count":25},{"id":"2003.08974","title":"Latent Space Roadmap for Visual Action Planning of Deformable and Rigid Object Manipulation","created":"2020-03-19","cited_by_count":25},{"id":"2001.04296","title":"High-Fidelity Synthesis with Disentangled Representation","created":"2020-01-13","cited_by_count":23},{"id":"1901.10251","title":"Multi-Agent Reinforcement Learning with Multi-Step Generative Models","created":"2019-01-29","cited_by_count":18},{"id":"1903.04053","title":"Affordance Learning for End-to-End Visuomotor Robot Control","created":"2019-03-10","cited_by_count":18},{"id":"1905.10836","title":"OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization","created":"2019-05-26","cited_by_count":17},{"id":"1703.04070","title":"Prediction and Control with Temporal Segment Models","created":"2017-03-12","cited_by_count":14},{"id":"2203.08949","title":"Latent-Variable Advantage-Weighted Policy Optimization for Offline RL","created":"2022-03-16","cited_by_count":12},{"id":"1910.06031","title":"Imitating by generating: deep generative models for imitation of interactive tasks","created":"2019-10-14","cited_by_count":11},{"id":"2105.12486","title":"GeomCA: Geometric Evaluation of Data Representations","created":"2021-05-26","cited_by_count":9},{"id":"1909.07745","title":"Adversarial Feature Training for Generalizable Robotic Visuomotor Control","created":"2019-09-17","cited_by_count":7},{"id":"2202.06866","title":"Delaunay Component Analysis for Evaluation of Data Representations","created":"2022-02-14","cited_by_count":6},{"id":"1804.10500","title":"Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments","created":"2018-04-27","cited_by_count":4},{"id":"1708.02313","title":"GPLAC: Generalizing Vision-Based Robotic Skills using Weakly Labeled Images","created":"2017-08-07","cited_by_count":3},{"id":"2003.04474","title":"Learning a generative model for robot control using visual feedback","created":"2020-03-10","cited_by_count":1}],"next_cursor":null}