{"list":"other","total":61,"rows":[{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"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":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1712.09707","title":"Deep learning for universal linear embeddings of nonlinear dynamics","created":"2017-12-27","cited_by_count":494},{"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":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"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":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"id":"1709.07523","title":"Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances","created":"2017-09-21","cited_by_count":201},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"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":"1710.04340","title":"Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition","created":"2017-10-12","cited_by_count":158},{"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":"2211.01364","title":"An optimal control perspective on diffusion-based generative modeling","created":"2022-11-02","cited_by_count":147},{"id":"1901.10031","title":"Lyapunov-based Safe Policy Optimization for Continuous Control","created":"2019-01-28","cited_by_count":145},{"id":"2005.00611","title":"Neural Lyapunov Control","created":"2020-05-01","cited_by_count":142},{"id":"2011.05869","title":"CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee","created":"2020-11-11","cited_by_count":134},{"id":"2307.11046","title":"A Definition of Continual Reinforcement Learning","created":"2023-07-20","cited_by_count":101},{"id":"2309.05837","title":"The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems","created":"2023-09-11","cited_by_count":88},{"id":"2205.07536","title":"Reachability Constrained Reinforcement Learning","created":"2022-05-16","cited_by_count":59},{"id":"2302.03122","title":"State-wise Safe Reinforcement Learning: A Survey","created":"2023-02-06","cited_by_count":55},{"id":"2104.02808","title":"Robust Control Barrier-Value Functions for Safety-Critical Control","created":"2021-04-06","cited_by_count":51},{"id":"2112.12288","title":"Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning","created":"2021-12-23","cited_by_count":49},{"id":"1410.6445","title":"Reach-Avoid Problems with Time-Varying Dynamics, Targets and Constraints","created":"2014-10-23","cited_by_count":44},{"id":"2309.13528","title":"Iterative Reachability Estimation for Safe Reinforcement Learning","created":"2023-09-24","cited_by_count":37},{"id":"2107.04989","title":"Stabilizing Neural Control Using Self-Learned Almost Lyapunov Critics","created":"2021-07-11","cited_by_count":35},{"id":"2103.01556","title":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","created":"2021-03-02","cited_by_count":32},{"id":"2105.10682","title":"Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety","created":"2021-05-22","cited_by_count":30},{"id":"2212.03228","title":"ISAACS: Iterative Soft Adversarial Actor-Critic for Safety","created":"2022-12-06","cited_by_count":28},{"id":"2201.08355","title":"Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees","created":"2022-01-20","cited_by_count":27},{"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":"1605.01799","title":"Algorithms for Overcoming the Curse of Dimensionality for Certain Hamilton-Jacobi Equations Arising in Control Theory and Elsewhere","created":"2016-05-06","cited_by_count":24},{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24},{"id":"2305.14154","title":"Solving Stabilize-Avoid Optimal Control via Epigraph Form and Deep Reinforcement Learning","created":"2023-05-23","cited_by_count":24},{"id":"1806.06161","title":"BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning","created":"2018-06-16","cited_by_count":23},{"id":"2103.11575","title":"Learn-to-Race: A Multimodal Control Environment for Autonomous Racing","created":"2021-03-22","cited_by_count":23},{"id":"1806.04225","title":"PAC-Bayes Control: Learning Policies that Provably Generalize to Novel Environments","created":"2018-06-11","cited_by_count":22},{"id":"2202.07565","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","created":"2022-02-15","cited_by_count":20},{"id":"1611.00122","title":"Decomposition of Reachable Sets and Tubes for a Class of Nonlinear Systems","created":"2016-11-01","cited_by_count":18},{"id":"2210.07553","title":"Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate","created":"2022-10-14","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":"1911.11397","title":"Adaptive dynamic programming for nonaffine nonlinear optimal control problem with state constraints","created":"2019-11-26","cited_by_count":12},{"id":"1809.00706","title":"A Minimum Discounted Reward Hamilton-Jacobi Formulation for Computing Reachable Sets","created":"2018-09-03","cited_by_count":11},{"id":"2204.05520","title":"OptimizedDP: An Efficient, User-friendly Library For Optimal Control and Dynamic Programming","created":"2022-04-12","cited_by_count":11},{"id":"2207.13891","title":"Quantifying Safety of Learning-based Self-Driving Control Using Almost-Barrier Functions","created":"2022-07-28","cited_by_count":10},{"id":"2303.02215","title":"Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Models","created":"2023-03-03","cited_by_count":10},{"id":"1704.02524","title":"Algorithm for Overcoming the Curse of Dimensionality for State-dependent Hamilton-Jacobi equations","created":"2017-04-08","cited_by_count":7},{"id":"1811.03643","title":"Voronoi Partition-based Scenario Reduction for Fast Sampling-based Stochastic Reachability Computation of LTI Systems","created":"2018-11-08","cited_by_count":4},{"id":"1602.08150","title":"Reachability-Based Safety and Goal Satisfaction of Unmanned Aerial Platoons on Air Highways","created":"2016-02-25","cited_by_count":3},{"id":"1603.05205","title":"Fast Reachable Set Approximations via State Decoupling Disturbances","created":"2016-03-16","cited_by_count":2},{"id":"1903.06448","title":"Initial Data Identification in Conservation Laws and Hamilton-Jacobi Equations","created":"2019-03-15","cited_by_count":2},{"id":"1302.5990","title":"A Modified Riccati Transformation for Decentralized Computation of the Viability Kernel Under LTI Dynamics","created":"2013-02-25","cited_by_count":1},{"id":"1709.06590","title":"Time-Optimal Collaborative Guidance Using the Generalized Hopf Formula","created":"2017-09-19","cited_by_count":1},{"id":"2303.11590","title":"Koopman-Hopf Hamilton-Jacobi Reachability and Control","created":"2023-03-21","cited_by_count":1}],"next_cursor":null}