{"list":"other","total":86,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"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":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"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":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"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":"1804.10332","title":"Sim-to-Real: Learning Agile Locomotion For Quadruped Robots","created":"2018-04-27","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":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"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":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"1709.04905","title":"One-Shot Visual Imitation Learning via Meta-Learning","created":"2017-09-14","cited_by_count":228},{"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":"1811.12560","title":"An Introduction to Deep Reinforcement Learning","created":"2018-11-30","cited_by_count":206},{"id":"1909.11652","title":"Deep Dynamics Models for Learning Dexterous Manipulation","created":"2019-09-25","cited_by_count":206},{"id":"1407.3501","title":"Robots that can adapt like animals","created":"2014-07-13","cited_by_count":204},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"1802.10567","title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","created":"2018-02-28","cited_by_count":167},{"id":"1812.06298","title":"Residual Policy Learning","created":"2018-12-15","cited_by_count":164},{"id":"1812.11103","title":"Learning to Walk via Deep Reinforcement Learning","created":"2018-12-26","cited_by_count":158},{"id":"1606.07419","title":"Learning to Poke by Poking: Experiential Learning of Intuitive Physics","created":"2016-06-23","cited_by_count":154},{"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":"2003.13661","title":"Multi-Task Reinforcement Learning with Soft Modularization","created":"2020-03-30","cited_by_count":143},{"id":"2011.10024","title":"Parrot: Data-Driven Behavioral Priors for Reinforcement Learning","created":"2020-11-19","cited_by_count":138},{"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":"1804.08606","title":"Zero-Shot Visual Imitation","created":"2018-04-23","cited_by_count":117},{"id":"1805.01956","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","created":"2018-05-04","cited_by_count":111},{"id":"1905.09808","title":"MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies","created":"2019-05-23","cited_by_count":108},{"id":"1610.04286","title":"Sim-to-Real Robot Learning from Pixels with Progressive Nets","created":"2016-10-13","cited_by_count":94},{"id":"1709.10082","title":"Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning","created":"2017-09-28","cited_by_count":83},{"id":"2010.14500","title":"COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning","created":"2020-10-27","cited_by_count":83},{"id":"1812.07671","title":"Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL","created":"2018-12-18","cited_by_count":81},{"id":"2010.14484","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","created":"2020-10-27","cited_by_count":79},{"id":"1807.07049","title":"Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias","created":"2018-07-18","cited_by_count":75},{"id":"1810.03237","title":"Task-Embedded Control Networks for Few-Shot Imitation Learning","created":"2018-10-08","cited_by_count":66},{"id":"1612.06699","title":"Unsupervised Perceptual Rewards for Imitation Learning","created":"2016-12-20","cited_by_count":65},{"id":"1806.10166","title":"Modular meta-learning","created":"2018-06-26","cited_by_count":51},{"id":"2107.00646","title":"Learning to See before Learning to Act: Visual Pre-training for Manipulation","created":"2021-07-01","cited_by_count":51},{"id":"2010.14274","title":"Behavior Priors for Efficient Reinforcement Learning","created":"2020-10-27","cited_by_count":41},{"id":"2012.03548","title":"Reset-Free Lifelong Learning with Skill-Space Planning","created":"2020-12-07","cited_by_count":38},{"id":"1907.05855","title":"DisCoRL: Continual Reinforcement Learning via Policy Distillation","created":"2019-07-11","cited_by_count":36},{"id":"1911.01103","title":"Learning One-Shot Imitation from Humans without Humans","created":"2019-11-04","cited_by_count":33},{"id":"1703.00727","title":"Deep Predictive Policy Training using Reinforcement Learning","created":"2017-03-02","cited_by_count":32},{"id":"2103.15793","title":"LASER: Learning a Latent Action Space for Efficient Reinforcement Learning","created":"2021-03-29","cited_by_count":32},{"id":"2007.15588","title":"Data-efficient Hindsight Off-policy Option Learning","created":"2020-07-30","cited_by_count":31},{"id":"2007.07011","title":"Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting","created":"2020-07-14","cited_by_count":29},{"id":"2010.06491","title":"Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning","created":"2020-10-13","cited_by_count":26},{"id":"1610.04213","title":"Reset-free Trial-and-Error Learning for Robot Damage Recovery","created":"2016-10-13","cited_by_count":24},{"id":"2103.14610","title":"SKID RAW: Skill Discovery from Raw Trajectories","created":"2021-03-26","cited_by_count":22},{"id":"1911.05071","title":"Experience-Embedded Visual Foresight","created":"2019-11-12","cited_by_count":21},{"id":"2103.07607","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","created":"2021-03-13","cited_by_count":19},{"id":"1903.04053","title":"Affordance Learning for End-to-End Visuomotor Robot Control","created":"2019-03-10","cited_by_count":18},{"id":"2011.04627","title":"Learning to Compose Hierarchical Object-Centric Controllers for Robotic Manipulation","created":"2020-11-09","cited_by_count":17},{"id":"2103.10972","title":"Learning Task Decomposition with Ordered Memory Policy Network","created":"2021-03-19","cited_by_count":15},{"id":"1903.09537","title":"Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie","created":"2019-03-22","cited_by_count":14},{"id":"1909.12324","title":"Learning Generalizable Locomotion Skills with Hierarchical Reinforcement Learning","created":"2019-09-26","cited_by_count":13},{"id":"1907.07029","title":"Adaptive Prior Selection for Repertoire-based Online Adaptation in Robotics","created":"2019-07-16","cited_by_count":11},{"id":"2011.01054","title":"Information-theoretic Task Selection for Meta-Reinforcement Learning","created":"2020-11-02","cited_by_count":10},{"id":"2101.04178","title":"Action Priors for Large Action Spaces in Robotics","created":"2021-01-11","cited_by_count":10},{"id":"1902.05542","title":"Unsupervised Visuomotor Control through Distributional Planning Networks","created":"2019-02-14","cited_by_count":9},{"id":"1709.06917","title":"Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics","created":"2017-09-20","cited_by_count":6},{"id":"1809.10253","title":"Scaling simulation-to-real transfer by learning composable robot skills","created":"2018-09-26","cited_by_count":6},{"id":"1910.09471","title":"Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer","created":"2019-10-21","cited_by_count":5},{"id":"2012.14464","title":"Disentangled Planning and Control in Vision Based Robotics via Reward Machines","created":"2020-12-28","cited_by_count":5},{"id":"1906.06178","title":"Curriculum Learning for Cumulative Return Maximization","created":"2019-06-13","cited_by_count":4},{"id":"1911.06636","title":"Catch & Carry: Reusable Neural Controllers for Vision-Guided Whole-Body Tasks","created":"2019-11-15","cited_by_count":4},{"id":"2011.07318","title":"A Geometric Perspective on Self-Supervised Policy Adaptation","created":"2020-11-14","cited_by_count":4},{"id":"2102.05207","title":"Transfer Reinforcement Learning across Homotopy Classes","created":"2021-02-10","cited_by_count":4},{"id":"2010.15492","title":"\"What, not how\": Solving an under-actuated insertion task from scratch","created":"2020-10-29","cited_by_count":1},{"id":"2012.01934","title":"Adaptable Automation with Modular Deep Reinforcement Learning and Policy Transfer","created":"2020-11-27","cited_by_count":1}],"next_cursor":null}