{"list":"other","total":51,"rows":[{"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":"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":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"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":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1903.08792","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","created":"2019-03-21","cited_by_count":289},{"id":"1801.08757","title":"Safe Exploration in Continuous Action Spaces","created":"2018-01-26","cited_by_count":247},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"1810.05687","title":"Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience","created":"2018-10-12","cited_by_count":217},{"id":"1702.03920","title":"Cognitive Mapping and Planning for Visual Navigation","created":"2017-02-13","cited_by_count":212},{"id":"1709.07523","title":"Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances","created":"2017-09-21","cited_by_count":201},{"id":"2006.03875","title":"Coresets via Bilevel Optimization for Continual Learning and Streaming","created":"2020-06-06","cited_by_count":192},{"id":"2010.15920","title":"Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones","created":"2020-10-29","cited_by_count":175},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"1705.01292","title":"A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems","created":"2017-05-03","cited_by_count":163},{"id":"1901.05353","title":"A Primer on PAC-Bayesian Learning","created":"2019-01-16","cited_by_count":132},{"id":"1803.08287","title":"Learning-based Model Predictive Control for Safe Exploration","created":"2018-03-22","cited_by_count":120},{"id":"2010.14603","title":"Learning to be Safe: Deep RL with a Safety Critic","created":"2020-10-27","cited_by_count":116},{"id":"2007.12911","title":"Tighter risk certificates for neural networks","created":"2020-07-25","cited_by_count":112},{"id":"1406.3339","title":"Algorithms for CVaR Optimization in MDPs","created":"2014-06-12","cited_by_count":99},{"id":"1711.06782","title":"Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning","created":"2017-11-18","cited_by_count":90},{"id":"1702.01182","title":"Uncertainty-Aware Reinforcement Learning for Collision Avoidance","created":"2017-02-03","cited_by_count":88},{"id":"1906.01728","title":"BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators","created":"2019-06-04","cited_by_count":85},{"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":"1509.01066","title":"Safe Controller Optimization for Quadrotors with Gaussian Processes","created":"2015-09-03","cited_by_count":78},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63},{"id":"1903.02531","title":"Combining Optimal Control and Learning for Visual Navigation in Novel Environments","created":"2019-03-06","cited_by_count":52},{"id":"2112.12288","title":"Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning","created":"2021-12-23","cited_by_count":49},{"id":"2003.02471","title":"Data-efficient Domain Randomization with Bayesian Optimization","created":"2020-03-05","cited_by_count":47},{"id":"1410.6445","title":"Reach-Avoid Problems with Time-Varying Dynamics, Targets and Constraints","created":"2014-10-23","cited_by_count":44},{"id":"2111.04814","title":"Planar Robot Casting with Real2Sim2Real Self-Supervised Learning","created":"2021-11-08","cited_by_count":39},{"id":"1912.04226","title":"Unsupervised Curricula for Visual Meta-Reinforcement Learning","created":"2019-12-09","cited_by_count":34},{"id":"2001.07934","title":"Safe Robot Navigation via Multi-Modal Anomaly Detection","created":"2020-01-22","cited_by_count":34},{"id":"1601.04037","title":"Funnel Libraries for Real-Time Robust Feedback Motion Planning","created":"2016-01-15","cited_by_count":29},{"id":"2012.03390","title":"On Infusing Reachability-Based Safety Assurance within Planning Frameworks for Human-Robot Vehicle Interactions","created":"2020-12-06","cited_by_count":25},{"id":"1906.05819","title":"Robust Regression for Safe Exploration in Control","created":"2019-06-13","cited_by_count":24},{"id":"1806.04225","title":"PAC-Bayes Control: Learning Policies that Provably Generalize to Novel Environments","created":"2018-06-11","cited_by_count":22},{"id":"1905.00532","title":"An Efficient Reachability-Based Framework for Provably Safe Autonomous Navigation in Unknown Environments","created":"2019-05-01","cited_by_count":18},{"id":"2002.12852","title":"Probably Approximately Correct Vision-Based Planning using Motion Primitives","created":"2020-02-28","cited_by_count":16},{"id":"2110.07699","title":"Safe Autonomous Racing via Approximate Reachability on Ego-vision","created":"2021-10-14","cited_by_count":13},{"id":"1912.10120","title":"Generating Robust Supervision for Learning-Based Visual Navigation Using Hamilton-Jacobi Reachability","created":"2019-12-20","cited_by_count":4},{"id":"2111.08733","title":"Learning Provably Robust Motion Planners Using Funnel Libraries","created":"2021-11-16","cited_by_count":1},{"id":"2111.08761","title":"Stronger Generalization Guarantees for Robot Learning by Combining Generative Models and Real-World Data","created":"2021-11-16","cited_by_count":1}],"next_cursor":null}