{"list":"other","total":57,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"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":"1906.00331","title":"On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems","created":"2019-06-02","cited_by_count":270},{"id":"2005.06392","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","created":"2020-05-13","cited_by_count":264},{"id":"1801.05039","title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","created":"2018-01-15","cited_by_count":250},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"id":"2007.06558","title":"Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization","created":"2020-07-13","cited_by_count":176},{"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":"1909.01150","title":"Neural Policy Gradient Methods: Global Optimality and Rates of Convergence","created":"2019-08-29","cited_by_count":159},{"id":"1910.13393","title":"Constrained Reinforcement Learning Has Zero Duality Gap","created":"2019-10-29","cited_by_count":151},{"id":"1906.01786","title":"Global Optimality Guarantees For Policy Gradient Methods","created":"2019-06-05","cited_by_count":150},{"id":"2003.02189","title":"Exploration-Exploitation in Constrained MDPs","created":"2020-03-04","cited_by_count":149},{"id":"1902.08297","title":"Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods","created":"2019-02-21","cited_by_count":148},{"id":"2003.00534","title":"Provably Efficient Safe Exploration via Primal-Dual Policy Optimization","created":"2020-03-01","cited_by_count":134},{"id":"2011.05869","title":"CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee","created":"2020-11-11","cited_by_count":134},{"id":"1910.09615","title":"IPO: Interior-point Policy Optimization under Constraints","created":"2019-10-21","cited_by_count":132},{"id":"1906.08383","title":"Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies","created":"2019-06-19","cited_by_count":124},{"id":"1909.02769","title":"Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs","created":"2019-09-06","cited_by_count":118},{"id":"1306.2119","title":"Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)","created":"2013-06-10","cited_by_count":111},{"id":"2007.02151","title":"Variational Policy Gradient Method for Reinforcement Learning with General Utilities","created":"2020-07-04","cited_by_count":111},{"id":"1708.03741","title":"Online Convex Optimization with Stochastic Constraints","created":"2017-08-12","cited_by_count":95},{"id":"2007.08459","title":"PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning","created":"2020-07-16","cited_by_count":92},{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80},{"id":"1806.07555","title":"Stagewise Safe Bayesian Optimization with Gaussian Processes","created":"2018-06-20","cited_by_count":79},{"id":"1911.09101","title":"Safe Policies for Reinforcement Learning via Primal-Dual Methods","created":"2019-11-20","cited_by_count":79},{"id":"1812.08305","title":"Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems","created":"2018-12-20","cited_by_count":67},{"id":"1802.06480","title":"Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning","created":"2018-02-19","cited_by_count":62},{"id":"1910.12156","title":"Convergent Policy Optimization for Safe Reinforcement Learning","created":"2019-10-26","cited_by_count":57},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53},{"id":"2007.11120","title":"On Linear Convergence of Policy Gradient Methods for Finite MDPs","created":"2020-07-21","cited_by_count":52},{"id":"2109.06332","title":"Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach","created":"2021-09-13","cited_by_count":50},{"id":"1802.06472","title":"Online convex optimization for cumulative constraints","created":"2018-02-19","cited_by_count":47},{"id":"1912.11899","title":"Convergence and sample complexity of gradient methods for the model-free linear quadratic regulator problem","created":"2019-12-26","cited_by_count":46},{"id":"2001.09377","title":"Constrained Upper Confidence Reinforcement Learning","created":"2020-01-26","cited_by_count":46},{"id":"2002.09621","title":"Global Convergence and Variance-Reduced Optimization for a Class of Nonconvex-Nonconcave Minimax Problems","created":"2020-02-22","cited_by_count":38},{"id":"2106.06239","title":"Safe Reinforcement Learning with Linear Function Approximation","created":"2021-06-11","cited_by_count":35},{"id":"2110.08923","title":"A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization","created":"2021-10-17","cited_by_count":34},{"id":"2008.11811","title":"Constrained Markov Decision Processes via Backward Value Functions","created":"2020-08-26","cited_by_count":33},{"id":"1908.00305","title":"Online Primal-Dual Mirror Descent under Stochastic Constraints","created":"2019-08-01","cited_by_count":31},{"id":"2107.05216","title":"A Simple Reward-free Approach to Constrained Reinforcement Learning","created":"2021-07-12","cited_by_count":30},{"id":"2110.10116","title":"On the Global Optimum Convergence of Momentum-based Policy Gradient","created":"2021-10-19","cited_by_count":26},{"id":"2111.00552","title":"Policy Optimization for Constrained MDPs with Provable Fast Global Convergence","created":"2021-10-31","cited_by_count":23},{"id":"2102.03192","title":"Provably Efficient Algorithms for Multi-Objective Competitive RL","created":"2021-02-05","cited_by_count":22},{"id":"2002.12435","title":"Learning in Markov Decision Processes under Constraints","created":"2020-02-27","cited_by_count":20},{"id":"2110.10351","title":"Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process","created":"2021-10-20","cited_by_count":19},{"id":"2110.11383","title":"Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes","created":"2021-10-21","cited_by_count":17},{"id":"1606.03000","title":"On Projected Stochastic Gradient Descent Algorithm with Weighted Averaging for Least Squares Regression","created":"2016-06-09","cited_by_count":9},{"id":"2204.05176","title":"Towards Painless Policy Optimization for Constrained MDPs","created":"2022-04-11","cited_by_count":8},{"id":"1911.04220","title":"Non-Cooperative Inverse Reinforcement Learning","created":"2019-11-03","cited_by_count":7},{"id":"2007.04203","title":"A Natural Actor-Critic Algorithm with Downside Risk Constraints","created":"2020-07-08","cited_by_count":2}],"next_cursor":null}