{"list":"other","total":60,"rows":[{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"1903.11199","title":"Control Barrier Functions: Theory and Applications","created":"2019-03-27","cited_by_count":372},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"2007.03964","title":"Responsive Safety in Reinforcement Learning by PID Lagrangian Methods","created":"2020-07-08","cited_by_count":316},{"id":"1805.07708","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","created":"2018-05-20","cited_by_count":297},{"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":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213},{"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":"1711.08013","title":"OSQP: An Operator Splitting Solver for Quadratic Programs","created":"2017-11-21","cited_by_count":161},{"id":"2306.14874","title":"ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots","created":"2023-06-26","cited_by_count":152},{"id":"2202.11762","title":"Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methods","created":"2022-02-23","cited_by_count":151},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149},{"id":"1901.10031","title":"Lyapunov-based Safe Policy Optimization for Continuous Control","created":"2019-01-28","cited_by_count":145},{"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":"2003.00534","title":"Provably Efficient Safe Exploration via Primal-Dual Policy Optimization","created":"2020-03-01","cited_by_count":134},{"id":"1910.09615","title":"IPO: Interior-point Policy Optimization under Constraints","created":"2019-10-21","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":"2310.10943","title":"Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning","created":"2023-10-17","cited_by_count":111},{"id":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101},{"id":"2004.03315","title":"Learning Control Barrier Functions from Expert Demonstrations","created":"2020-04-07","cited_by_count":92},{"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":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64},{"id":"2209.15090","title":"Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments","created":"2022-09-29","cited_by_count":60},{"id":"2110.05415","title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","created":"2021-10-11","cited_by_count":59},{"id":"1910.12156","title":"Convergent Policy Optimization for Safe Reinforcement Learning","created":"2019-10-26","cited_by_count":57},{"id":"2106.09110","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","created":"2021-06-16","cited_by_count":47},{"id":"2002.12156","title":"Cautious Reinforcement Learning with Logical Constraints","created":"2020-02-26","cited_by_count":45},{"id":"2206.04436","title":"Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk","created":"2022-06-09","cited_by_count":41},{"id":"1402.0560","title":"Safe Exploration of State and Action Spaces in Reinforcement Learning","created":"2014-02-04","cited_by_count":38},{"id":"2006.09436","title":"SAMBA: Safe Model-Based & Active Reinforcement Learning","created":"2020-06-12","cited_by_count":30},{"id":"2211.11056","title":"Safe Control Under Input Limits with Neural Control Barrier Functions","created":"2022-11-20","cited_by_count":29},{"id":"2011.08421","title":"Reachability-based Trajectory Safeguard (RTS): A Safe and Fast Reinforcement Learning Safety Layer for Continuous Control","created":"2020-11-17","cited_by_count":28},{"id":"2204.07417","title":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","created":"2022-04-15","cited_by_count":26},{"id":"2210.10691","title":"Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes","created":"2022-10-19","cited_by_count":26},{"id":"2109.05120","title":"TERP: Reliable Planning in Uneven Outdoor Environments using Deep Reinforcement Learning","created":"2021-09-10","cited_by_count":20},{"id":"2112.03850","title":"Policy Search for Model Predictive Control with Application to Agile Drone Flight","created":"2021-12-07","cited_by_count":20},{"id":"2112.13941","title":"Safe Reinforcement Learning with Chance-constrained Model Predictive Control","created":"2021-12-27","cited_by_count":20},{"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":"2205.06311","title":"Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environments","created":"2022-05-12","cited_by_count":18},{"id":"2201.09562","title":"GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems","created":"2022-01-24","cited_by_count":17},{"id":"2209.13308","title":"Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction","created":"2022-09-27","cited_by_count":17},{"id":"2203.04739","title":"Regularized Deep Signed Distance Fields for Reactive Motion Generation","created":"2022-03-09","cited_by_count":16},{"id":"1505.05798","title":"Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret","created":"2015-05-21","cited_by_count":15},{"id":"2010.08669","title":"Robot Learning with Crash Constraints","created":"2020-10-16","cited_by_count":15},{"id":"2210.00629","title":"Convex synthesis and verification of control-Lyapunov and barrier functions with input constraints","created":"2022-10-02","cited_by_count":14},{"id":"2102.08539","title":"Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning","created":"2021-02-17","cited_by_count":13},{"id":"2103.09230","title":"Lyapunov Barrier Policy Optimization","created":"2021-03-16","cited_by_count":12},{"id":"2107.01309","title":"Towards safe human-to-robot handovers of unknown containers","created":"2021-07-03","cited_by_count":11},{"id":"2306.17279","title":"Probabilistic Constraint for Safety-Critical Reinforcement Learning","created":"2023-06-29","cited_by_count":11},{"id":"2312.00342","title":"Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk","created":"2023-12-01","cited_by_count":11},{"id":"2301.04330","title":"Fast Kinodynamic Planning on the Constraint Manifold with Deep Neural Networks","created":"2023-01-11","cited_by_count":9},{"id":"2107.06140","title":"Efficient and Reactive Planning for High Speed Robot Air Hockey","created":"2021-07-13","cited_by_count":8},{"id":"2004.12553","title":"Differentiating through Log-Log Convex Programs","created":"2020-04-27","cited_by_count":7},{"id":"2208.01103","title":"Safe and Efficient Exploration of Human Models During Human-Robot Interaction","created":"2022-08-01","cited_by_count":3}],"next_cursor":null}