{"list":"other","total":78,"rows":[{"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":"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":"2007.03964","title":"Responsive Safety in Reinforcement Learning by PID Lagrangian Methods","created":"2020-07-08","cited_by_count":316},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"2007.06558","title":"Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization","created":"2020-07-13","cited_by_count":176},{"id":"1909.01150","title":"Neural Policy Gradient Methods: Global Optimality and Rates of Convergence","created":"2019-08-29","cited_by_count":159},{"id":"2102.00135","title":"Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes","created":"2021-01-30","cited_by_count":156},{"id":"1910.13393","title":"Constrained Reinforcement Learning Has Zero Duality Gap","created":"2019-10-29","cited_by_count":151},{"id":"2003.02189","title":"Exploration-Exploitation in Constrained MDPs","created":"2020-03-04","cited_by_count":149},{"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":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124},{"id":"2202.04634","title":"Offline Reinforcement Learning with Realizability and Single-policy Concentrability","created":"2022-02-09","cited_by_count":123},{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119},{"id":"1807.04252","title":"Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization","created":"2018-07-11","cited_by_count":98},{"id":"1908.08465","title":"On the convergence of single-call stochastic extra-gradient methods","created":"2019-08-22","cited_by_count":89},{"id":"2105.11066","title":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","created":"2021-05-24","cited_by_count":84},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84},{"id":"2009.09623","title":"The Complexity of Constrained Min-Max Optimization","created":"2020-09-21","cited_by_count":82},{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80},{"id":"1911.09101","title":"Safe Policies for Reinforcement Learning via Primal-Dual Methods","created":"2019-11-20","cited_by_count":79},{"id":"2102.04540","title":"Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games","created":"2021-02-08","cited_by_count":69},{"id":"2105.15186","title":"Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization","created":"2021-05-31","cited_by_count":63},{"id":"1910.12156","title":"Convergent Policy Optimization for Safe Reinforcement Learning","created":"2019-10-26","cited_by_count":57},{"id":"1804.06500","title":"Two-Player Games for Efficient Non-Convex Constrained Optimization","created":"2018-04-17","cited_by_count":55},{"id":"2008.12776","title":"Efficiently Solving MDPs with Stochastic Mirror Descent","created":"2020-08-28","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":"2001.09377","title":"Constrained Upper Confidence Reinforcement Learning","created":"2020-01-26","cited_by_count":46},{"id":"2003.00660","title":"Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss","created":"2020-03-02","cited_by_count":46},{"id":"2210.01400","title":"Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies","created":"2022-10-04","cited_by_count":46},{"id":"2101.10895","title":"A Primal-Dual Approach to Constrained Markov Decision Processes","created":"2021-01-26","cited_by_count":42},{"id":"2102.11941","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards","created":"2021-02-23","cited_by_count":40},{"id":"2206.06270","title":"Near-Optimal Sample Complexity Bounds for Constrained MDPs","created":"2022-06-13","cited_by_count":37},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35},{"id":"2006.05051","title":"Constrained episodic reinforcement learning in concave-convex and knapsack settings","created":"2020-06-09","cited_by_count":34},{"id":"2009.11348","title":"A Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints","created":"2020-09-23","cited_by_count":34},{"id":"2110.08923","title":"A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization","created":"2021-10-17","cited_by_count":34},{"id":"2206.11889","title":"Provably Efficient Model-Free Constrained RL with Linear Function Approximation","created":"2022-06-23","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":"2303.02738","title":"Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback","created":"2023-03-05","cited_by_count":30},{"id":"2202.00150","title":"Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints","created":"2022-01-31","cited_by_count":29},{"id":"2202.06626","title":"MuZero with Self-competition for Rate Control in VP9 Video Compression","created":"2022-02-14","cited_by_count":28},{"id":"1502.04968","title":"Projected Reflected Gradient Methods for Monotone Variational Inequalities","created":"2015-02-17","cited_by_count":27},{"id":"1906.02027","title":"Last-iterate convergence rates for min-max optimization","created":"2019-06-05","cited_by_count":25},{"id":"2110.10117","title":"Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization","created":"2021-10-19","cited_by_count":25},{"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":"1711.05812","title":"Iteration complexity of inexact augmented Lagrangian methods for constrained convex programming","created":"2017-11-15","cited_by_count":21},{"id":"2002.06768","title":"Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes","created":"2020-02-17","cited_by_count":21},{"id":"2303.05733","title":"Provably Efficient Model-Free Algorithms for Non-stationary CMDPs","created":"2023-03-10","cited_by_count":21},{"id":"2002.12435","title":"Learning in Markov Decision Processes under Constraints","created":"2020-02-27","cited_by_count":20},{"id":"2202.07565","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","created":"2022-02-15","cited_by_count":20},{"id":"2206.05248","title":"Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion","created":"2022-06-10","cited_by_count":20},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","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":"2204.09228","title":"Tight Last-Iterate Convergence of the Extragradient and the Optimistic Gradient Descent-Ascent Algorithm for Constrained Monotone Variational Inequalities","created":"2022-04-20","cited_by_count":19},{"id":"2002.12475","title":"Cautious Reinforcement Learning via Distributional Risk in the Dual Domain","created":"2020-02-27","cited_by_count":18},{"id":"2010.06324","title":"Balancing Constraints and Rewards with Meta-Gradient D4PG","created":"2020-10-13","cited_by_count":18},{"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":"2206.05357","title":"Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning","created":"2022-06-10","cited_by_count":15},{"id":"2303.03095","title":"Can We Find Nash Equilibria at a Linear Rate in Markov Games?","created":"2023-03-03","cited_by_count":9},{"id":"2304.14326","title":"A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints","created":"2023-04-27","cited_by_count":9},{"id":"2204.05176","title":"Towards Painless Policy Optimization for Constrained MDPs","created":"2022-04-11","cited_by_count":8},{"id":"2210.04527","title":"A policy gradient approach for Finite Horizon Constrained Markov Decision Processes","created":"2022-10-10","cited_by_count":8},{"id":"1603.05738","title":"On the non-ergodic convergence rate of an inexact augmented Lagrangian framework for composite convex programming","created":"2016-03-18","cited_by_count":7},{"id":"2301.11547","title":"Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation","created":"2023-01-27","cited_by_count":6},{"id":"1502.03123","title":"A Universal Primal-Dual Convex Optimization Framework","created":"2015-02-10","cited_by_count":5},{"id":"2205.10715","title":"Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction","created":"2022-05-22","cited_by_count":5},{"id":"2206.01666","title":"Algorithm for Constrained Markov Decision Process with Linear Convergence","created":"2022-06-03","cited_by_count":4},{"id":"2010.14314","title":"Faster Lagrangian-Based Methods in Convex Optimization","created":"2020-10-27","cited_by_count":3},{"id":"2212.01505","title":"Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics","created":"2022-12-03","cited_by_count":3},{"id":"1806.05280","title":"Augmented Lagrangian-Based Decomposition Methods with Non-Ergodic Optimal Rates","created":"2018-06-13","cited_by_count":1},{"id":"2304.02459","title":"Lagrangian-based methods in convex optimization: prediction-correction frameworks with non-ergodic convergence rates","created":"2023-04-05","cited_by_count":1}],"next_cursor":null}