{"list":"other","total":54,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"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":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1901.08652","title":"Learning agile and dynamic motor skills for legged robots","created":"2019-01-24","cited_by_count":504},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"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":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305},{"id":"1702.03920","title":"Cognitive Mapping and Planning for Visual Navigation","created":"2017-02-13","cited_by_count":212},{"id":"1812.11103","title":"Learning to Walk via Deep Reinforcement Learning","created":"2018-12-26","cited_by_count":158},{"id":"2011.01975","title":"Rearrangement: A Challenge for Embodied AI","created":"2020-11-03","cited_by_count":155},{"id":"2011.07215","title":"SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation","created":"2020-11-14","cited_by_count":121},{"id":"1804.09627","title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","created":"2018-04-25","cited_by_count":103},{"id":"2103.16544","title":"Visual Room Rearrangement","created":"2021-03-30","cited_by_count":102},{"id":"1910.14442","title":"Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environments","created":"2019-10-30","cited_by_count":90},{"id":"1805.06066","title":"Visual Representations for Semantic Target Driven Navigation","created":"2018-05-15","cited_by_count":89},{"id":"1604.03670","title":"Interactive Perception: Leveraging Action in Perception and Perception in Action","created":"2016-04-13","cited_by_count":78},{"id":"1910.13439","title":"Learning to Manipulate Deformable Objects without Demonstrations","created":"2019-10-29","cited_by_count":77},{"id":"1904.04686","title":"Multi-Target Embodied Question Answering","created":"2019-04-09","cited_by_count":74},{"id":"1911.07246","title":"IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks","created":"2019-11-17","cited_by_count":69},{"id":"1902.07742","title":"From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following","created":"2019-02-20","cited_by_count":67},{"id":"1906.08880","title":"Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks","created":"2019-06-20","cited_by_count":67},{"id":"2103.14025","title":"The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI","created":"2021-03-25","cited_by_count":65},{"id":"1905.09275","title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","created":"2019-05-22","cited_by_count":57},{"id":"1810.11181","title":"Neural Modular Control for Embodied Question Answering","created":"2018-10-26","cited_by_count":56},{"id":"1903.02749","title":"Deep Visual MPC-Policy Learning for Navigation","created":"2019-03-07","cited_by_count":56},{"id":"1910.11432","title":"HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators","created":"2019-10-24","cited_by_count":55},{"id":"1903.02531","title":"Combining Optimal Control and Learning for Visual Navigation in Novel Environments","created":"2019-03-06","cited_by_count":52},{"id":"2008.07792","title":"ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation","created":"2020-08-18","cited_by_count":49},{"id":"1601.05484","title":"Analysis and Observations from the First Amazon Picking Challenge","created":"2016-01-21","cited_by_count":41},{"id":"1902.03701","title":"Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight","created":"2019-02-11","cited_by_count":28},{"id":"1905.13146","title":"Gaze-in-wild: A dataset for studying eye and head coordination in everyday activities","created":"2019-05-09","cited_by_count":25}],"next_cursor":null}