{"list":"other","total":70,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"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":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2003.04960","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","created":"2020-03-10","cited_by_count":373},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"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":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"1905.10520","title":"6-DOF GraspNet: Variational Grasp Generation for Object Manipulation","created":"2019-05-25","cited_by_count":242},{"id":"1702.03920","title":"Cognitive Mapping and Planning for Visual Navigation","created":"2017-02-13","cited_by_count":212},{"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":"2005.12256","title":"Neural Topological SLAM for Visual Navigation","created":"2020-05-25","cited_by_count":195},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"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":"1803.09956","title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","created":"2018-03-27","cited_by_count":128},{"id":"1710.01330","title":"Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching","created":"2017-10-03","cited_by_count":125},{"id":"2007.04309","title":"Self-Supervised Policy Adaptation during Deployment","created":"2020-07-08","cited_by_count":123},{"id":"1804.05172","title":"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach","created":"2018-04-14","cited_by_count":120},{"id":"2002.08550","title":"Learning to Walk in the Real World with Minimal Human Effort","created":"2020-02-20","cited_by_count":111},{"id":"1912.04344","title":"Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations","created":"2019-12-09","cited_by_count":107},{"id":"1904.03461","title":"Embodied Question Answering in Photorealistic Environments with Point Cloud Perception","created":"2019-04-06","cited_by_count":103},{"id":"2002.05700","title":"BADGR: An Autonomous Self-Supervised Learning-Based Navigation System","created":"2020-02-13","cited_by_count":102},{"id":"2004.14646","title":"Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning","created":"2020-04-30","cited_by_count":102},{"id":"2104.11213","title":"ManipulaTHOR: A Framework for Visual Object Manipulation","created":"2021-04-22","cited_by_count":102},{"id":"1703.00420","title":"Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation","created":"2017-03-01","cited_by_count":98},{"id":"1609.05521","title":"Playing FPS Games with Deep Reinforcement Learning","created":"2016-09-18","cited_by_count":95},{"id":"1702.01182","title":"Uncertainty-Aware Reinforcement Learning for Collision Avoidance","created":"2017-02-03","cited_by_count":88},{"id":"1709.10082","title":"Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning","created":"2017-09-28","cited_by_count":83},{"id":"1709.10489","title":"Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation","created":"2017-09-29","cited_by_count":77},{"id":"1912.03628","title":"6-DOF Grasping for Target-driven Object Manipulation in Clutter","created":"2019-12-08","cited_by_count":70},{"id":"1906.09237","title":"Shaping Belief States with Generative Environment Models for RL","created":"2019-06-21","cited_by_count":66},{"id":"1802.06480","title":"Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning","created":"2018-02-19","cited_by_count":62},{"id":"1910.11432","title":"HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators","created":"2019-10-24","cited_by_count":55},{"id":"2007.04561","title":"Auxiliary Tasks Speed Up Learning PointGoal Navigation","created":"2020-07-09","cited_by_count":54},{"id":"2008.12760","title":"AllenAct: A Framework for Embodied AI Research","created":"2020-08-28","cited_by_count":54},{"id":"2106.04531","title":"RobustNav: Towards Benchmarking Robustness in Embodied Navigation","created":"2021-06-08","cited_by_count":54},{"id":"1910.11689","title":"Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning","created":"2019-10-24","cited_by_count":49},{"id":"2103.10534","title":"Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation","created":"2021-03-18","cited_by_count":44},{"id":"1811.06407","title":"Neural Predictive Belief Representations","created":"2018-11-15","cited_by_count":40},{"id":"2004.09141","title":"Spatial Action Maps for Mobile Manipulation","created":"2020-04-20","cited_by_count":31},{"id":"1601.04037","title":"Funnel Libraries for Real-Time Robust Feedback Motion Planning","created":"2016-01-15","cited_by_count":29},{"id":"1706.04652","title":"Learning a visuomotor controller for real world robotic grasping using simulated depth images","created":"2017-06-14","cited_by_count":29},{"id":"1603.00622","title":"PLATO: Policy Learning using Adaptive Trajectory Optimization","created":"2016-03-02","cited_by_count":24},{"id":"1607.08665","title":"Introspective Perception: Learning to Predict Failures in Vision Systems","created":"2016-07-28","cited_by_count":17},{"id":"1806.06134","title":"Learning 6-DoF Grasping and Pick-Place Using Attention Focus","created":"2018-06-15","cited_by_count":7},{"id":"2012.06117","title":"How to Train PointGoal Navigation Agents on a (Sample and Compute) Budget","created":"2020-12-11","cited_by_count":7},{"id":"1401.4599","title":"Learning and Reasoning with Action-Related Places for Robust Mobile Manipulation","created":"2014-01-18","cited_by_count":3}],"next_cursor":null}