{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"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":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1707.08817","title":"Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","created":"2017-07-27","cited_by_count":319},{"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":"1812.03201","title":"Residual Reinforcement Learning for Robot Control","created":"2018-12-07","cited_by_count":274},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"1810.02890","title":"HG-DAgger: Interactive Imitation Learning with Human Experts","created":"2018-10-05","cited_by_count":266},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"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":"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":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"1810.10191","title":"Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks","created":"2018-10-24","cited_by_count":154},{"id":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"1801.02209","title":"Building Generalizable Agents with a Realistic and Rich 3D Environment","created":"2018-01-07","cited_by_count":109},{"id":"2109.08273","title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","created":"2021-09-17","cited_by_count":108},{"id":"1903.03878","title":"Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks","created":"2019-03-09","cited_by_count":107},{"id":"1805.11085","title":"More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch","created":"2018-05-28","cited_by_count":102},{"id":"2011.01819","title":"Learning Representations from Audio-Visual Spatial Alignment","created":"2020-11-03","cited_by_count":95},{"id":"1702.08360","title":"Neural Map: Structured Memory for Deep Reinforcement Learning","created":"2017-02-27","cited_by_count":90},{"id":"1805.06066","title":"Visual Representations for Semantic Target Driven Navigation","created":"2018-05-15","cited_by_count":89},{"id":"1605.06450","title":"Query-Efficient Imitation Learning for End-to-End Autonomous Driving","created":"2016-05-20","cited_by_count":84},{"id":"2109.07991","title":"ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations","created":"2021-09-16","cited_by_count":68},{"id":"1906.06322","title":"Connecting Touch and Vision via Cross-Modal Prediction","created":"2019-06-14","cited_by_count":66},{"id":"1605.09128","title":"Control of Memory, Active Perception, and Action in Minecraft","created":"2016-05-30","cited_by_count":61},{"id":"2007.03669","title":"See, Hear, Explore: Curiosity via Audio-Visual Association","created":"2020-07-07","cited_by_count":43},{"id":"2007.03778","title":"3D Shape Reconstruction from Vision and Touch","created":"2020-07-07","cited_by_count":42},{"id":"2011.01968","title":"Learning 3D Dynamic Scene Representations for Robot Manipulation","created":"2020-11-03","cited_by_count":39},{"id":"2106.08050","title":"Residual Reinforcement Learning from Demonstrations","created":"2021-06-15","cited_by_count":31},{"id":"1903.01588","title":"Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter","created":"2019-03-04","cited_by_count":30},{"id":"2009.07083","title":"Event-Driven Visual-Tactile Sensing and Learning for Robots","created":"2020-09-15","cited_by_count":29},{"id":"2003.03518","title":"Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands","created":"2020-03-07","cited_by_count":26},{"id":"1811.08067","title":"Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions","created":"2018-11-20","cited_by_count":25},{"id":"2004.10190","title":"Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning","created":"2020-04-21","cited_by_count":23},{"id":"2102.09754","title":"VisuoSpatial Foresight for Physical Sequential Fabric Manipulation","created":"2021-02-19","cited_by_count":18},{"id":"2111.05846","title":"Structure from Silence: Learning Scene Structure from Ambient Sound","created":"2021-11-10","cited_by_count":17},{"id":"2007.01851","title":"Swoosh! Rattle! Thump! -- Actions that Sound","created":"2020-07-03","cited_by_count":15},{"id":"2101.00733","title":"Occlusion-robust Deformable Object Tracking without Physics Simulation","created":"2021-01-04","cited_by_count":15},{"id":"1610.04871","title":"Probabilistic Articulated Real-Time Tracking for Robot Manipulation","created":"2016-10-16","cited_by_count":13},{"id":"2011.03334","title":"Occlusion-Aware Search for Object Retrieval in Clutter","created":"2020-11-06","cited_by_count":12},{"id":"2007.11646","title":"Understanding Multi-Modal Perception Using Behavioral Cloning for Peg-In-a-Hole Insertion Tasks","created":"2020-07-22","cited_by_count":9},{"id":"2112.06442","title":"Contact-Rich Manipulation of a Flexible Object based on Deep Predictive Learning using Vision and Tactility","created":"2021-12-13","cited_by_count":9},{"id":"2004.09039","title":"X-Ray: Mechanical Search for an Occluded Object by Minimizing Support of Learned Occupancy Distributions","created":"2020-04-20","cited_by_count":7},{"id":"2007.13729","title":"Noisy Agents: Self-supervised Exploration by Predicting Auditory Events","created":"2020-07-27","cited_by_count":5},{"id":"2008.09622","title":"Learning to Set Waypoints for Audio-Visual Navigation","created":"2020-08-21","cited_by_count":5},{"id":"2012.15436","title":"Robotic Grasping of Fully-Occluded Objects using RF Perception","created":"2020-12-31","cited_by_count":5},{"id":"1603.03833","title":"From virtual demonstration to real-world manipulation using LSTM and MDN","created":"2016-03-12","cited_by_count":3},{"id":"1911.09233","title":"Contextual Reinforcement Learning of Visuo-tactile Multi-fingered Grasping Policies","created":"2019-11-21","cited_by_count":3},{"id":"2103.01296","title":"Learning Multimodal Contact-Rich Skills from Demonstrations Without Reward Engineering","created":"2021-03-01","cited_by_count":2}],"next_cursor":null}