{"list":"other","total":62,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"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":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"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":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2004.02857","title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","created":"2020-04-06","cited_by_count":441},{"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":"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":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1810.08272","title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","created":"2018-10-18","cited_by_count":244},{"id":"1811.12354","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","created":"2018-11-29","cited_by_count":239},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"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":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229},{"id":"1709.04905","title":"One-Shot Visual Imitation Learning via Meta-Learning","created":"2017-09-14","cited_by_count":228},{"id":"1611.01796","title":"Modular Multitask Reinforcement Learning with Policy Sketches","created":"2016-11-06","cited_by_count":203},{"id":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"1802.01557","title":"One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning","created":"2018-02-05","cited_by_count":148},{"id":"1906.07343","title":"Language as an Abstraction for Hierarchical Deep Reinforcement Learning","created":"2019-06-18","cited_by_count":138},{"id":"2010.12083","title":"Language-Conditioned Imitation Learning for Robot Manipulation Tasks","created":"2020-10-22","cited_by_count":136},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125},{"id":"1904.07854","title":"End-to-End Robotic Reinforcement Learning without Reward Engineering","created":"2019-04-16","cited_by_count":122},{"id":"2103.16817","title":"Learning Generalizable Robotic Reward Functions from \"In-The-Wild\" Human Videos","created":"2021-03-31","cited_by_count":119},{"id":"2012.05292","title":"Topological Planning with Transformers for Vision-and-Language Navigation","created":"2020-12-09","cited_by_count":116},{"id":"1903.02020","title":"Using Natural Language for Reward Shaping in Reinforcement Learning","created":"2019-03-05","cited_by_count":114},{"id":"1706.06551","title":"Grounded Language Learning in a Simulated 3D World","created":"2017-06-20","cited_by_count":100},{"id":"1706.05064","title":"Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning","created":"2017-06-15","cited_by_count":98},{"id":"1909.05829","title":"Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation","created":"2019-09-12","cited_by_count":83},{"id":"1704.08795","title":"Mapping Instructions and Visual Observations to Actions with Reinforcement Learning","created":"2017-04-28","cited_by_count":81},{"id":"1806.01946","title":"Learning to Understand Goal Specifications by Modelling Reward","created":"2018-06-05","cited_by_count":80},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","cited_by_count":75},{"id":"1706.07230","title":"Gated-Attention Architectures for Task-Oriented Language Grounding","created":"2017-06-22","cited_by_count":72},{"id":"1805.11686","title":"Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition","created":"2018-05-29","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":"2005.09382","title":"Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text","created":"2020-05-19","cited_by_count":59},{"id":"1506.04089","title":"Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences","created":"2015-06-12","cited_by_count":50},{"id":"1606.02447","title":"Learning Language Games through Interaction","created":"2016-06-08","cited_by_count":43},{"id":"1910.09664","title":"Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight","created":"2019-10-21","cited_by_count":43},{"id":"2012.15373","title":"Model-Based Visual Planning with Self-Supervised Functional Distances","created":"2020-12-30","cited_by_count":42},{"id":"2103.05825","title":"ELLA: Exploration through Learned Language Abstraction","created":"2021-03-10","cited_by_count":42},{"id":"1811.07882","title":"Guiding Policies with Language via Meta-Learning","created":"2018-11-19","cited_by_count":35},{"id":"2007.15543","title":"PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards","created":"2020-07-30","cited_by_count":30},{"id":"2010.06491","title":"Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning","created":"2020-10-13","cited_by_count":26},{"id":"1704.05539","title":"Beating Atari with Natural Language Guided Reinforcement Learning","created":"2017-04-18","cited_by_count":24},{"id":"1707.03938","title":"Representation Learning for Grounded Spatial Reasoning","created":"2017-07-13","cited_by_count":23},{"id":"2010.13957","title":"MELD: Meta-Reinforcement Learning from Images via Latent State Models","created":"2020-10-26","cited_by_count":22},{"id":"1508.06491","title":"Alignment-based compositional semantics for instruction following","created":"2015-08-26","cited_by_count":21},{"id":"1911.05071","title":"Experience-Embedded Visual Foresight","created":"2019-11-12","cited_by_count":21},{"id":"1704.06616","title":"Accurately and Efficiently Interpreting Human-Robot Instructions of Varying Granularities","created":"2017-04-21","cited_by_count":19},{"id":"1902.04546","title":"ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning","created":"2019-02-12","cited_by_count":17},{"id":"1706.06383","title":"Programmable Agents","created":"2017-06-20","cited_by_count":14},{"id":"2010.11917","title":"Batch Exploration with Examples for Scalable Robotic Reinforcement Learning","created":"2020-10-22","cited_by_count":14},{"id":"1910.09451","title":"HIGhER : Improving instruction following with Hindsight Generation for Experience Replay","created":"2019-10-21","cited_by_count":13},{"id":"2103.13861","title":"Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving","created":"2021-03-25","cited_by_count":9},{"id":"2104.11707","title":"DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies","created":"2021-04-23","cited_by_count":9},{"id":"2102.11137","title":"Program Synthesis Guided Reinforcement Learning for Partially Observed Environments","created":"2021-02-22","cited_by_count":8},{"id":"2001.09373","title":"Following Instructions by Imagining and Reaching Visual Goals","created":"2020-01-25","cited_by_count":6},{"id":"2102.13195","title":"Reinforcement Learning of Implicit and Explicit Control Flow in Instructions","created":"2021-02-25","cited_by_count":4}],"next_cursor":null}