{"list":"other","total":89,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"1903.11199","title":"Control Barrier Functions: Theory and Applications","created":"2019-03-27","cited_by_count":372},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","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":"1805.07708","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","created":"2018-05-20","cited_by_count":297},{"id":"1906.04893","title":"Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks","created":"2019-06-12","cited_by_count":293},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"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":"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":"1806.09460","title":"A Tour of Reinforcement Learning: The View from Continuous Control","created":"2018-06-25","cited_by_count":151},{"id":"1901.10031","title":"Lyapunov-based Safe Policy Optimization for Continuous Control","created":"2019-01-28","cited_by_count":145},{"id":"1610.01283","title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","created":"2016-10-05","cited_by_count":138},{"id":"1602.04450","title":"Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Robotics","created":"2016-02-14","cited_by_count":134},{"id":"1812.05506","title":"A predictive safety filter for learning-based control of constrained nonlinear dynamical systems","created":"2018-12-13","cited_by_count":118},{"id":"2010.14603","title":"Learning to be Safe: Deep RL with a Safety Critic","created":"2020-10-27","cited_by_count":116},{"id":"2010.14497","title":"Conservative Safety Critics for Exploration","created":"2020-10-27","cited_by_count":113},{"id":"1711.09883","title":"AI Safety Gridworlds","created":"2017-11-27","cited_by_count":110},{"id":"1705.10702","title":"Cautious Model Predictive Control using Gaussian Process Regression","created":"2017-05-30","cited_by_count":91},{"id":"1702.01182","title":"Uncertainty-Aware Reinforcement Learning for Collision Avoidance","created":"2017-02-03","cited_by_count":88},{"id":"1808.00924","title":"The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems","created":"2018-08-02","cited_by_count":88},{"id":"1811.08027","title":"Neural Lander: Stable Drone Landing Control using Learned Dynamics","created":"2018-11-19","cited_by_count":85},{"id":"1806.07555","title":"Stagewise Safe Bayesian Optimization with Gaussian Processes","created":"2018-06-20","cited_by_count":79},{"id":"2003.11881","title":"An empirical investigation of the challenges of real-world reinforcement learning","created":"2020-03-24","cited_by_count":77},{"id":"2103.02142","title":"Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control","created":"2021-03-03","cited_by_count":77},{"id":"1905.09727","title":"Deep Drone Racing: From Simulation to Reality with Domain Randomization","created":"2019-05-21","cited_by_count":76},{"id":"1606.04753","title":"Safe Exploration in Finite Markov Decision Processes with Gaussian Processes","created":"2016-06-15","cited_by_count":75},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"1709.07643","title":"OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World","created":"2017-09-22","cited_by_count":70},{"id":"1912.10099","title":"Learning for Safety-Critical Control with Control Barrier Functions","created":"2019-12-20","cited_by_count":69},{"id":"2004.07584","title":"Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions","created":"2020-04-16","cited_by_count":68},{"id":"2008.01825","title":"Robust Reinforcement Learning using Adversarial Populations","created":"2020-08-04","cited_by_count":66},{"id":"2102.05371","title":"Risk-Averse Offline Reinforcement Learning","created":"2021-02-10","cited_by_count":65},{"id":"1802.06480","title":"Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning","created":"2018-02-19","cited_by_count":62},{"id":"1904.00511","title":"Risk Averse Robust Adversarial Reinforcement Learning","created":"2019-03-31","cited_by_count":57},{"id":"1706.06491","title":"Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control","created":"2017-06-20","cited_by_count":53},{"id":"2104.02808","title":"Robust Control Barrier-Value Functions for Safety-Critical Control","created":"2021-04-06","cited_by_count":51},{"id":"1910.12908","title":"Certified Adversarial Robustness for Deep Reinforcement Learning","created":"2019-10-28","cited_by_count":47},{"id":"2008.06622","title":"Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings","created":"2020-08-15","cited_by_count":42},{"id":"1609.01387","title":"Learning Model Predictive Control for iterative tasks. A Data-Driven Control Framework","created":"2016-09-06","cited_by_count":39},{"id":"2107.12045","title":"How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review","created":"2021-07-26","cited_by_count":39},{"id":"1803.08552","title":"Linear model predictive safety certification for learning-based control","created":"2018-03-22","cited_by_count":37},{"id":"1905.05380","title":"Control Regularization for Reduced Variance Reinforcement Learning","created":"2019-05-14","cited_by_count":37},{"id":"1710.05472","title":"Safe Learning of Quadrotor Dynamics Using Barrier Certificates","created":"2017-10-16","cited_by_count":35},{"id":"1807.02303","title":"A survey on policy search algorithms for learning robot controllers in a handful of trials","created":"2018-07-06","cited_by_count":35},{"id":"1809.10121","title":"Safely Learning to Control the Constrained Linear Quadratic Regulator","created":"2018-09-26","cited_by_count":33},{"id":"2008.11811","title":"Constrained Markov Decision Processes via Backward Value Functions","created":"2020-08-26","cited_by_count":33},{"id":"2010.16001","title":"Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions","created":"2020-10-30","cited_by_count":33},{"id":"1810.11505","title":"Stability-certified reinforcement learning: A control-theoretic perspective","created":"2018-10-26","cited_by_count":31},{"id":"2105.13281","title":"GoSafe: Globally Optimal Safe Robot Learning","created":"2021-05-27","cited_by_count":27},{"id":"2010.12645","title":"Towards Safe Policy Improvement for Non-Stationary MDPs","created":"2020-10-23","cited_by_count":26},{"id":"1910.00555","title":"Adaptive Safety with Control Barrier Functions","created":"2019-10-01","cited_by_count":25},{"id":"1906.10417","title":"Probabilistic model predictive safety certification for learning-based control","created":"2019-06-25","cited_by_count":22},{"id":"1903.01577","title":"Episodic Learning with Control Lyapunov Functions for Uncertain Robotic Systems","created":"2019-03-04","cited_by_count":19},{"id":"1910.02325","title":"Bayesian Learning-Based Adaptive Control for Safety Critical Systems","created":"2019-10-05","cited_by_count":19},{"id":"1801.09627","title":"Barrier-Certified Adaptive Reinforcement Learning with Applications to Brushbot Navigation","created":"2018-01-29","cited_by_count":18},{"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":"1906.12189","title":"Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning","created":"2019-06-27","cited_by_count":16},{"id":"1910.13399","title":"Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization","created":"2019-10-29","cited_by_count":16},{"id":"2101.09505","title":"Safe Learning and Optimization Techniques: Towards a Survey of the State of the Art","created":"2021-01-23","cited_by_count":16},{"id":"1804.09831","title":"Adaptive MPC for Iterative Tasks","created":"2018-04-25","cited_by_count":15},{"id":"1909.08602","title":"Deep Model Reference Adaptive Control","created":"2019-09-18","cited_by_count":14},{"id":"2002.01587","title":"Deep Learning Tubes for Tube MPC","created":"2020-02-05","cited_by_count":14},{"id":"2011.10730","title":"Towards Robust Data-Driven Control Synthesis for Nonlinear Systems with Actuation Uncertainty","created":"2020-11-21","cited_by_count":14},{"id":"2101.05916","title":"Scalable Learning of Safety Guarantees for Autonomous Systems using Hamilton-Jacobi Reachability","created":"2021-01-15","cited_by_count":14},{"id":"2011.02920","title":"Asynchronous Deep Model Reference Adaptive Control","created":"2020-11-04","cited_by_count":13},{"id":"2004.14594","title":"$\\mathcal{L}_1$-$\\mathcal{GP}$: $\\mathcal{L}_1$ Adaptive Control with Bayesian Learning","created":"2020-04-30","cited_by_count":11},{"id":"1804.01031","title":"Provably Robust Learning-Based Approach for High-Accuracy Tracking Control of Lagrangian Systems","created":"2018-04-03","cited_by_count":10},{"id":"1912.10116","title":"Probabilistic Safety Constraints for Learned High Relative Degree System Dynamics","created":"2019-12-20","cited_by_count":9},{"id":"2003.07489","title":"Catch the Ball: Accurate High-Speed Motions for Mobile Manipulators via Inverse Dynamics Learning","created":"2020-03-17","cited_by_count":8},{"id":"2004.08752","title":"Zeus: A System Description of the Two-Time Winner of the Collegiate SAE AutoDrive Competition","created":"2020-04-19","cited_by_count":8},{"id":"1911.02899","title":"A robust adaptive model predictive control framework for nonlinear uncertain systems","created":"2019-11-07","cited_by_count":7},{"id":"2003.08028","title":"A Control Barrier Perspective on Episodic Learning via Projection-to-State Safety","created":"2020-03-18","cited_by_count":7},{"id":"1903.07214","title":"A Control Lyapunov Perspective on Episodic Learning via Projection to State Stability","created":"2019-03-18","cited_by_count":4},{"id":"2105.07668","title":"Probabilistic Robust Linear Quadratic Regulators with Gaussian Processes","created":"2021-05-17","cited_by_count":4},{"id":"2003.08613","title":"Controller Design via Experimental Exploration with Robustness Guarantees","created":"2020-03-19","cited_by_count":3},{"id":"1804.09790","title":"Adaptive MPC with Chance Constraints for FIR Systems","created":"2018-04-25","cited_by_count":2}],"next_cursor":null}