{"list":"other","total":47,"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":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"2005.06392","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","created":"2020-05-13","cited_by_count":264},{"id":"1903.08738","title":"Batch Policy Learning under Constraints","created":"2019-03-20","cited_by_count":244},{"id":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178},{"id":"1703.07710","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","created":"2017-03-22","cited_by_count":176},{"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":"2001.01866","title":"Reinforcement Learning via Fenchel-Rockafellar Duality","created":"2020-01-07","cited_by_count":100},{"id":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84},{"id":"2112.01506","title":"Sample Complexity of Robust Reinforcement Learning with a Generative Model","created":"2021-12-02","cited_by_count":83},{"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":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69},{"id":"1906.09323","title":"Reinforcement Learning with Convex Constraints","created":"2019-06-21","cited_by_count":60},{"id":"2006.09484","title":"Partial Policy Iteration for L1-Robust Markov Decision Processes","created":"2020-06-16","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":"2001.09377","title":"Constrained Upper Confidence Reinforcement Learning","created":"2020-01-26","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":"2212.10439","title":"Policy Gradient in Robust MDPs with Global Convergence Guarantee","created":"2022-12-20","cited_by_count":38},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","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":"2008.00311","title":"Learning with Safety Constraints: Sample Complexity of Reinforcement Learning for Constrained MDPs","created":"2020-08-01","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":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28},{"id":"2005.05434","title":"Scalable First-Order Methods for Robust MDPs","created":"2020-05-11","cited_by_count":25},{"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":"2010.04870","title":"Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty","created":"2020-10-10","cited_by_count":23},{"id":"2302.05372","title":"Towards Minimax Optimality of Model-based Robust Reinforcement Learning","created":"2023-02-10","cited_by_count":22},{"id":"2205.14327","title":"Efficient Policy Iteration for Robust Markov Decision Processes via Regularization","created":"2022-05-28","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":"2106.01577","title":"A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes","created":"2021-06-03","cited_by_count":17},{"id":"2010.10644","title":"Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification","created":"2020-10-20","cited_by_count":16},{"id":"2209.06866","title":"Robust Constrained Reinforcement Learning","created":"2022-09-14","cited_by_count":15},{"id":"1801.04745","title":"Distributionally Robust Optimization for Sequential Decision Making","created":"2018-01-15","cited_by_count":12},{"id":"2302.01248","title":"Robust Markov Decision Processes without Model Estimation","created":"2023-02-02","cited_by_count":11},{"id":"2209.10187","title":"On the convex formulations of robust Markov decision processes","created":"2022-09-21","cited_by_count":10},{"id":"2405.01327","title":"Constrained Reinforcement Learning Under Model Mismatch","created":"2024-05-02","cited_by_count":8},{"id":"1805.10406","title":"Robust Nonparametric Regression under Huber's $\\epsilon$-contamination Model","created":"2018-05-26","cited_by_count":6},{"id":"2112.15364","title":"Robust Entropy-regularized Markov Decision Processes","created":"2021-12-31","cited_by_count":4},{"id":"2406.10406","title":"Methods of Nonconvex Optimization","created":"2024-06-14","cited_by_count":3},{"id":"2308.03297","title":"Approximate Constrained Discounted Dynamic Programming with Uniform Feasibility and Optimality","created":"2023-08-07","cited_by_count":1}],"next_cursor":null}