{"list":"other","total":59,"rows":[{"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":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"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":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"1709.10089","title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","created":"2017-09-28","cited_by_count":340},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"2010.01083","title":"Integrated Task and Motion Planning","created":"2020-10-02","cited_by_count":290},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1703.09312","title":"Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics","created":"2017-03-27","cited_by_count":264},{"id":"1809.10790","title":"Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects","created":"2018-09-27","cited_by_count":241},{"id":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229},{"id":"2010.11944","title":"Accelerating Reinforcement Learning with Learned Skill Priors","created":"2020-10-22","cited_by_count":223},{"id":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"2101.02692","title":"Where2Act: From Pixels to Actions for Articulated 3D Objects","created":"2021-01-07","cited_by_count":182},{"id":"2010.13611","title":"OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning","created":"2020-10-26","cited_by_count":166},{"id":"1911.08453","title":"Planning with Goal-Conditioned Policies","created":"2019-11-19","cited_by_count":149},{"id":"2011.10024","title":"Parrot: Data-Driven Behavioral Priors for Reinforcement Learning","created":"2020-11-19","cited_by_count":138},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"1709.07326","title":"AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection","created":"2017-09-21","cited_by_count":128},{"id":"1309.2660","title":"Data-Driven Grasp Synthesis - A Survey","created":"2013-09-10","cited_by_count":106},{"id":"1911.05321","title":"IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data","created":"2019-11-13","cited_by_count":86},{"id":"2009.01439","title":"Learning Dexterous Grasping with Object-Centric Visual Affordances","created":"2020-09-03","cited_by_count":85},{"id":"1710.01813","title":"Neural Task Programming: Learning to Generalize Across Hierarchical Tasks","created":"2017-10-04","cited_by_count":76},{"id":"1511.04143","title":"Deep Reinforcement Learning in Parameterized Action Space","created":"2015-11-13","cited_by_count":68},{"id":"2008.09241","title":"Learning Affordance Landscapes for Interaction Exploration in 3D Environments","created":"2020-08-21","cited_by_count":65},{"id":"1509.01644","title":"Reinforcement Learning with Parameterized Actions","created":"2015-09-05","cited_by_count":63},{"id":"1807.03480","title":"Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration","created":"2018-07-10","cited_by_count":61},{"id":"1810.06394","title":"Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space","created":"2018-10-10","cited_by_count":58},{"id":"1903.01344","title":"Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space","created":"2019-03-04","cited_by_count":54},{"id":"1806.02813","title":"Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings","created":"2018-06-07","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":"2006.06444","title":"Learning compositional models of robot skills for task and motion planning","created":"2020-06-08","cited_by_count":48},{"id":"1909.13874","title":"Efficient Bimanual Manipulation Using Learned Task Schemas","created":"2019-09-30","cited_by_count":45},{"id":"2001.00449","title":"Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics","created":"2020-01-02","cited_by_count":44},{"id":"1904.12691","title":"DAC: The Double Actor-Critic Architecture for Learning Options","created":"2019-04-29","cited_by_count":43},{"id":"2011.08424","title":"Deep Affordance Foresight: Planning Through What Can Be Done in the Future","created":"2020-11-17","cited_by_count":41},{"id":"1910.11669","title":"Learning Task-Oriented Grasping from Human Activity Datasets","created":"2019-10-25","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":"2005.10872","title":"Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning","created":"2020-05-21","cited_by_count":25},{"id":"2011.01928","title":"Generalization to New Actions in Reinforcement Learning","created":"2020-11-03","cited_by_count":25},{"id":"1712.00004","title":"Learnings Options End-to-End for Continuous Action Tasks","created":"2017-11-30","cited_by_count":24},{"id":"2011.08177","title":"A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects","created":"2020-11-16","cited_by_count":23},{"id":"2011.04627","title":"Learning to Compose Hierarchical Object-Centric Controllers for Robotic Manipulation","created":"2020-11-09","cited_by_count":17},{"id":"1810.09656","title":"Hierarchical Approaches for Reinforcement Learning in Parameterized Action Space","created":"2018-10-23","cited_by_count":15}],"next_cursor":null}