{"list":"other","total":61,"rows":[{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"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":"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":"1801.08757","title":"Safe Exploration in Continuous Action Spaces","created":"2018-01-26","cited_by_count":247},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"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":"2007.05170","title":"A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic","created":"2020-07-10","cited_by_count":144},{"id":"2011.05869","title":"CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee","created":"2020-11-11","cited_by_count":134},{"id":"2008.06626","title":"Safe Reinforcement Learning in Constrained Markov Decision Processes","created":"2020-08-15","cited_by_count":115},{"id":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96},{"id":"2102.06548","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","created":"2021-02-12","cited_by_count":92},{"id":"2112.01506","title":"Sample Complexity of Robust Reinforcement Learning with a Generative Model","created":"2021-12-02","cited_by_count":83},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69},{"id":"1802.06480","title":"Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning","created":"2018-02-19","cited_by_count":62},{"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":"2204.00755","title":"Safe Reinforcement Learning via Shielding under Partial Observability","created":"2022-04-02","cited_by_count":56},{"id":"1706.04711","title":"Reinforcement Learning under Model Mismatch","created":"2017-06-15","cited_by_count":52},{"id":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51},{"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":"2110.06267","title":"Twice regularized MDPs and the equivalence between robustness and regularization","created":"2021-10-12","cited_by_count":47},{"id":"2212.10439","title":"Policy Gradient in Robust MDPs with Global Convergence Guarantee","created":"2022-12-20","cited_by_count":38},{"id":"2206.06270","title":"Near-Optimal Sample Complexity Bounds for Constrained MDPs","created":"2022-06-13","cited_by_count":37},{"id":"2307.08875","title":"Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation","created":"2023-07-17","cited_by_count":36},{"id":"2307.16212","title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","created":"2023-07-30","cited_by_count":36},{"id":"2007.01174","title":"Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch","created":"2020-07-02","cited_by_count":33},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32},{"id":"2209.10579","title":"First-order Policy Optimization for Robust Markov Decision Process","created":"2022-09-21","cited_by_count":32},{"id":"2301.13589","title":"Policy Gradient for Rectangular Robust Markov Decision Processes","created":"2023-01-31","cited_by_count":31},{"id":"2007.12315","title":"Bayesian Robust Optimization for Imitation Learning","created":"2020-07-24","cited_by_count":28},{"id":"2005.05434","title":"Scalable First-Order Methods for Robust MDPs","created":"2020-05-11","cited_by_count":25},{"id":"2307.07907","title":"Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation","created":"2023-07-15","cited_by_count":25},{"id":"2010.04870","title":"Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty","created":"2020-10-10","cited_by_count":23},{"id":"2212.02705","title":"What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?","created":"2022-12-06","cited_by_count":22},{"id":"2006.00945","title":"Robust Reinforcement Learning with Wasserstein Constraint","created":"2020-06-01","cited_by_count":21},{"id":"2301.10923","title":"Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints","created":"2023-01-26","cited_by_count":21},{"id":"2405.01677","title":"Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation","created":"2024-05-02","cited_by_count":21},{"id":"2206.00833","title":"Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm","created":"2022-06-02","cited_by_count":20},{"id":"1405.6757","title":"Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces","created":"2014-05-26","cited_by_count":19},{"id":"2310.03718","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning","created":"2023-10-05","cited_by_count":18},{"id":"2403.09621","title":"Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning","created":"2024-03-14","cited_by_count":18},{"id":"1306.6189","title":"Scaling Up Robust MDPs by Reinforcement Learning","created":"2013-06-26","cited_by_count":17},{"id":"2306.17750","title":"TD Convergence: An Optimization Perspective","created":"2023-06-30","cited_by_count":16},{"id":"1612.02516","title":"Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning","created":"2016-12-08","cited_by_count":15},{"id":"2209.06866","title":"Robust Constrained Reinforcement Learning","created":"2022-09-14","cited_by_count":15},{"id":"1905.12185","title":"Geometric Insights into the Convergence of Nonlinear TD Learning","created":"2019-05-29","cited_by_count":13},{"id":"2209.08230","title":"A Robust and Constrained Multi-Agent Reinforcement Learning Electric Vehicle Rebalancing Method in AMoD Systems","created":"2022-09-17","cited_by_count":11},{"id":"2212.06988","title":"Efficient Exploration in Resource-Restricted Reinforcement Learning","created":"2022-12-14","cited_by_count":10},{"id":"2405.01327","title":"Constrained Reinforcement Learning Under Model Mismatch","created":"2024-05-02","cited_by_count":8},{"id":"2411.18612","title":"Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization","created":"2024-11-27","cited_by_count":8},{"id":"2210.07636","title":"Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning","created":"2022-10-14","cited_by_count":6},{"id":"2210.11201","title":"Robust Imitation via Mirror Descent Inverse Reinforcement Learning","created":"2022-10-20","cited_by_count":6},{"id":"2308.11139","title":"Rectangularity and duality of distributionally robust Markov Decision Processes","created":"2023-08-22","cited_by_count":6},{"id":"2412.19873","title":"Minimax-Optimal Multi-Agent Robust Reinforcement Learning","created":"2024-12-27","cited_by_count":5},{"id":"2505.18044","title":"Linear Mixture Distributionally Robust Markov Decision Processes","created":"2025-05-23","cited_by_count":5}],"next_cursor":null}