{"total":111,"rows":[{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364,"area":"offlinerl"},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279,"area":"offlinerl"},{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119,"area":null},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"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,"area":null},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"2107.11433","title":"A general sample complexity analysis of vanilla policy gradient","created":"2021-07-23","cited_by_count":76,"area":null},{"id":"2102.08607","title":"On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method","created":"2021-02-17","cited_by_count":70,"area":null},{"id":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69,"area":null},{"id":"2302.01734","title":"Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies","created":"2023-02-03","cited_by_count":58,"area":null},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56,"area":null},{"id":"2102.11270","title":"Softmax Policy Gradient Methods Can Take Exponential Time to Converge","created":"2021-02-22","cited_by_count":48,"area":null},{"id":"2105.01424","title":"On the Linear convergence of Natural Policy Gradient Algorithm","created":"2021-05-04","cited_by_count":48,"area":null},{"id":"2210.01400","title":"Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies","created":"2022-10-04","cited_by_count":46,"area":null},{"id":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37,"area":null},{"id":"2202.03060","title":"The Importance of Non-Markovianity in Maximum State Entropy Exploration","created":"2022-02-07","cited_by_count":35,"area":null},{"id":"2101.07012","title":"Regularized Policies are Reward Robust","created":"2021-01-18","cited_by_count":32,"area":null},{"id":"2202.01511","title":"Challenging Common Assumptions in Convex Reinforcement Learning","created":"2022-02-03","cited_by_count":30,"area":"offlinerl"},{"id":"2301.13139","title":"A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence","created":"2023-01-30","cited_by_count":30,"area":null},{"id":"2211.00716","title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian","created":"2022-11-01","cited_by_count":29,"area":"offlinerl"},{"id":"2206.02346","title":"Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2110.10116","title":"On the Global Optimum Convergence of Momentum-based Policy Gradient","created":"2021-10-19","cited_by_count":26,"area":null},{"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,"area":null},{"id":"2105.12540","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation","created":"2021-05-26","cited_by_count":22,"area":null},{"id":"2302.10261","title":"Deep Reinforcement Learning for Cost-Effective Medical Diagnosis","created":"2023-02-20","cited_by_count":21,"area":null},{"id":"2205.12856","title":"Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2109.05439","title":"Concave Utility Reinforcement Learning with Zero-Constraint Violations","created":"2021-09-12","cited_by_count":19,"area":null},{"id":"2412.18164","title":"Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence","created":"2024-12-24","cited_by_count":19,"area":"diffusion"},{"id":"2306.01854","title":"Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space","created":"2023-06-02","cited_by_count":18,"area":null},{"id":"2404.03372","title":"Elementary Analysis of Policy Gradient Methods","created":"2024-04-04","cited_by_count":18,"area":"deeprl"},{"id":"2511.22640","title":"Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning","created":"2025-11-27","cited_by_count":17,"area":"diffusion"},{"id":"2206.05357","title":"Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning","created":"2022-06-10","cited_by_count":15,"area":null},{"id":"2305.17568","title":"Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2308.09175","title":"Diversifying AI: Towards Creative Chess with AlphaZero","created":"2023-08-17","cited_by_count":15,"area":null},{"id":"2407.09905","title":"Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods","created":"2024-07-13","cited_by_count":15,"area":"deeprl"},{"id":"2301.12714","title":"Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning","created":"2023-01-30","cited_by_count":13,"area":"offlinerl"},{"id":"2105.14125","title":"Joint Optimization of Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2106.08414","title":"On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control","created":"2021-06-15","cited_by_count":12,"area":null},{"id":"2305.00303","title":"A Coupled Flow Approach to Imitation Learning","created":"2023-04-29","cited_by_count":12,"area":"offlinerl"},{"id":"2409.17401","title":"Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference","created":"2024-09-25","cited_by_count":12,"area":"alignment"},{"id":"2402.17722","title":"Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence","created":"2024-02-27","cited_by_count":11,"area":null},{"id":"2209.10187","title":"On the convex formulations of robust Markov decision processes","created":"2022-09-21","cited_by_count":10,"area":null},{"id":"2401.07043","title":"Quantum Advantage Actor-Critic for Reinforcement Learning","created":"2024-01-13","cited_by_count":9,"area":"deeprl"},{"id":"2401.14811","title":"On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Tasks","created":"2024-01-26","cited_by_count":9,"area":"deeprl"},{"id":"2403.06806","title":"On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes","created":"2024-03-11","cited_by_count":9,"area":"deeprl"},{"id":"2305.14608","title":"Inverse Reinforcement Learning with the Average Reward Criterion","created":"2023-05-24","cited_by_count":8,"area":"offlinerl"},{"id":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","cited_by_count":8,"area":null},{"id":"2109.06362","title":"Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods","created":"2021-09-13","cited_by_count":7,"area":null},{"id":"2405.13136","title":"Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs","created":"2024-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2208.00088","title":"Improved Policy Optimization for Online Imitation Learning","created":"2022-07-29","cited_by_count":6,"area":"offlinerl"},{"id":"2210.00991","title":"Policy Gradient for Reinforcement Learning with General Utilities","created":"2022-10-03","cited_by_count":6,"area":null},{"id":"2311.18346","title":"Efficient Model-Based Concave Utility Reinforcement Learning through Greedy Mirror Descent","created":"2023-11-30","cited_by_count":6,"area":null},{"id":"2401.01084","title":"Global Convergence of Natural Policy Gradient with Hessian-aided Momentum Variance Reduction","created":"2024-01-02","cited_by_count":6,"area":"deeprl"},{"id":"2407.13364","title":"Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2410.04108","title":"On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning","created":"2024-10-05","cited_by_count":6,"area":"offlinerl"},{"id":"2410.23498","title":"Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm","created":"2024-10-30","cited_by_count":6,"area":"deeprl"},{"id":"2106.00543","title":"MARL with General Utilities via Decentralized Shadow Reward Actor-Critic","created":"2021-05-29","cited_by_count":5,"area":null},{"id":"2111.00185","title":"Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings","created":"2021-10-30","cited_by_count":5,"area":null},{"id":"2302.03770","title":"Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability","created":"2023-02-07","cited_by_count":5,"area":"offlinerl"},{"id":"2303.08431","title":"Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators","created":"2023-03-15","cited_by_count":5,"area":null},{"id":"2407.12163","title":"Bellman Diffusion Models","created":"2024-07-16","cited_by_count":5,"area":"diffusion"},{"id":"2410.05673","title":"Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem","created":"2024-10-08","cited_by_count":5,"area":"deeprl"},{"id":"2304.12886","title":"What can online reinforcement learning with function approximation benefit from general coverage conditions?","created":"2023-04-25","cited_by_count":4,"area":"offlinerl"},{"id":"2401.00629","title":"Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning","created":"2024-01-01","cited_by_count":4,"area":"offlinerl"},{"id":"2405.19807","title":"MetaCURL: Non-stationary Concave Utility Reinforcement Learning","created":"2024-05-30","cited_by_count":4,"area":"deeprl"},{"id":"2412.14002","title":"Operator Splitting for Convex Constrained Markov Decision Processes","created":"2024-12-18","cited_by_count":4,"area":"deeprl"},{"id":"2502.08365","title":"Towards Principled Unsupervised Multi-Agent Reinforcement Learning","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2305.13289","title":"Achieving the Asymptotically Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach","created":"2023-05-22","cited_by_count":3,"area":"offlinerl"},{"id":"2409.15128","title":"The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2410.16600","title":"Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2509.18822","title":"On the Convergence of Policy Mirror Descent with Temporal Difference Evaluation","created":"2025-09-23","cited_by_count":3,"area":"deeprl"},{"id":"2602.06769","title":"Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities","created":"2026-02-06","cited_by_count":3,"area":"deeprl"},{"id":"2302.07938","title":"Scalable Multi-Agent Reinforcement Learning with General Utilities","created":"2023-02-15","cited_by_count":2,"area":null},{"id":"2303.07068","title":"n-Step Temporal Difference Learning with Optimal n","created":"2023-03-13","cited_by_count":2,"area":null},{"id":"2305.19575","title":"On the Linear Convergence of Policy Gradient under Hadamard Parameterization","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2402.10810","title":"Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning","created":"2024-02-16","cited_by_count":2,"area":"deeprl"},{"id":"2405.19024","title":"Inverse Concave-Utility Reinforcement Learning is Inverse Game Theory","created":"2024-05-29","cited_by_count":2,"area":"offlinerl"},{"id":"2512.16565","title":"Non-Asymptotic Global Convergence of PPO-Clip","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2602.08012","title":"A Unified Density Operator View of Flow Control and Merging","created":"2026-02-08","cited_by_count":2,"area":"diffusion"},{"id":"2603.08518","title":"Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning","created":"2026-03-09","cited_by_count":2,"area":"deeprl"},{"id":"2102.07889","title":"Distributionally-Constrained Policy Optimization via Unbalanced Optimal Transport","created":"2021-02-15","cited_by_count":1,"area":null},{"id":"2107.02711","title":"A Unified Off-Policy Evaluation Approach for General Value Function","created":"2021-07-06","cited_by_count":1,"area":null},{"id":"2111.05670","title":"DeCOM: Decomposed Policy for Constrained Cooperative Multi-Agent Reinforcement Learning","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2202.00076","title":"Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2210.13879","title":"Proximal Mean Field Learning in Shallow Neural Networks","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2307.04456","title":"Invex Programs: First Order Algorithms and Their Convergence","created":"2023-07-10","cited_by_count":1,"area":null},{"id":"2312.11863","title":"Neural Network Approximation for Pessimistic Offline Reinforcement Learning","created":"2023-12-19","cited_by_count":1,"area":"offlinerl"},{"id":"2401.12508","title":"On the Stochastic (Variance-Reduced) Proximal Gradient Method for Regularized Expected Reward Optimization","created":"2024-01-23","cited_by_count":1,"area":"deeprl"},{"id":"2404.16468","title":"A Dual Perspective of Reinforcement Learning for Imposing Policy Constraints","created":"2024-04-25","cited_by_count":1,"area":"deeprl"},{"id":"2505.15782","title":"Solving General-Utility Markov Decision Processes in the Single-Trial Regime with Online Planning","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2509.01432","title":"The Geometry of Nonlinear Reinforcement Learning","created":"2025-09-01","cited_by_count":1,"area":"deeprl"},{"id":"2602.12181","title":"Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria","created":"2026-02-12","cited_by_count":1,"area":"deeprl"},{"id":"2605.10909","title":"Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with $k$-step Policy Gradients","created":"2026-05-11","cited_by_count":1,"area":"deeprl"},{"id":"2605.24357","title":"Refined Analysis of Entropy-Regularized Actor-Critic","created":"2026-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2607.20152","title":"Active Inference as a Convex Markov Decision Process","created":"2026-07-22","cited_by_count":1,"area":"deeprl"},{"id":"2608.03562","title":"Robust General Utility for Reinforcement Learning","created":"2026-08-04","cited_by_count":1,"area":"deeprl"},{"id":"2201.08832","title":"Occupancy Information Ratio: Infinite-Horizon, Information-Directed, Parameterized Policy Search","created":"2022-01-21","cited_by_count":0,"area":null},{"id":"2202.08930","title":"A Distributed Algorithm for Measure-valued Optimization with Additive Objective","created":"2022-02-17","cited_by_count":0,"area":null},{"id":"2209.02424","title":"Cross apprenticeship learning framework: Properties and solution approaches","created":"2022-09-06","cited_by_count":0,"area":null}],"next_cursor":"100"}