{"total":176,"rows":[{"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,"area":null},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"area":"alignment"},{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2505.22094","title":"ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning","created":"2025-05-28","cited_by_count":97,"area":"diffusion"},{"id":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96,"area":null},{"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":"2405.19320","title":"Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF","created":"2024-05-29","cited_by_count":73,"area":"alignment"},{"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":"2105.15186","title":"Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization","created":"2021-05-31","cited_by_count":63,"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":"2110.06267","title":"Twice regularized MDPs and the equivalence between robustness and regularization","created":"2021-10-12","cited_by_count":47,"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":"2105.06072","title":"Leveraging Non-uniformity in First-order Non-convex Optimization","created":"2021-05-13","cited_by_count":44,"area":null},{"id":"2210.01808","title":"Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":42,"area":"offlinerl"},{"id":"2402.06886","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","created":"2024-02-10","cited_by_count":41,"area":"alignment"},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2101.10506","title":"Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm","created":"2021-01-26","cited_by_count":39,"area":null},{"id":"2307.08875","title":"Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation","created":"2023-07-17","cited_by_count":36,"area":null},{"id":"2110.08923","title":"A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization","created":"2021-10-17","cited_by_count":34,"area":null},{"id":"2205.05800","title":"Stochastic first-order methods for average-reward Markov decision processes","created":"2022-05-11","cited_by_count":32,"area":null},{"id":"2209.10579","title":"First-order Policy Optimization for Robust Markov Decision Process","created":"2022-09-21","cited_by_count":32,"area":null},{"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":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"area":null},{"id":"2105.08024","title":"Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting","created":"2021-05-17","cited_by_count":28,"area":null},{"id":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28,"area":null},{"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":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2210.01050","title":"Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games","created":"2022-10-03","cited_by_count":26,"area":null},{"id":"2212.14449","title":"Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games","created":"2022-12-29","cited_by_count":26,"area":null},{"id":"2302.07457","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","created":"2023-02-15","cited_by_count":26,"area":"wm"},{"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":"2301.06276","title":"The Role of Baselines in Policy Gradient Optimization","created":"2023-01-16","cited_by_count":25,"area":null},{"id":"2305.18505","title":"Provable Reward-Agnostic Preference-Based Reinforcement Learning","created":"2023-05-29","cited_by_count":25,"area":"alignment"},{"id":"2310.11677","title":"Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes","created":"2023-10-18","cited_by_count":25,"area":null},{"id":"2303.10257","title":"Recent Developments in Machine Learning Methods for Stochastic Control and Games","created":"2023-03-17","cited_by_count":24,"area":null},{"id":"2111.00552","title":"Policy Optimization for Constrained MDPs with Provable Fast Global Convergence","created":"2021-10-31","cited_by_count":23,"area":null},{"id":"2211.16715","title":"Policy Optimization over General State and Action Spaces","created":"2022-11-30","cited_by_count":23,"area":null},{"id":"2310.02951","title":"A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces","created":"2023-10-04","cited_by_count":23,"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":"2206.09495","title":"The Power of Regularization in Solving Extensive-Form Games","created":"2022-06-19","cited_by_count":21,"area":null},{"id":"2206.00833","title":"Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm","created":"2022-06-02","cited_by_count":20,"area":null},{"id":"2211.17116","title":"Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning","created":"2022-11-30","cited_by_count":20,"area":null},{"id":"2110.10351","title":"Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process","created":"2021-10-20","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":"2102.08903","title":"Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games","created":"2021-02-17","cited_by_count":18,"area":null},{"id":"2108.05828","title":"A general class of surrogate functions for stable and efficient reinforcement learning","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2110.15572","title":"Understanding the Effect of Stochasticity in Policy Optimization","created":"2021-10-29","cited_by_count":18,"area":null},{"id":"2302.11381","title":"Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes","created":"2023-02-22","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":"2411.15370","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers","created":"2024-11-22","cited_by_count":18,"area":"deeprl"},{"id":"2106.12112","title":"Bregman Gradient Policy Optimization","created":"2021-06-23","cited_by_count":17,"area":null},{"id":"2209.15382","title":"Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2106.04096","title":"Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation","created":"2021-06-08","cited_by_count":16,"area":null},{"id":"2110.08984","title":"Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs","created":"2021-10-18","cited_by_count":16,"area":null},{"id":"2206.02640","title":"Policy Optimization for Markov Games: Unified Framework and Faster Convergence","created":"2022-06-06","cited_by_count":16,"area":null},{"id":"2306.00629","title":"Identifiability and Generalizability in Constrained Inverse Reinforcement Learning","created":"2023-06-01","cited_by_count":16,"area":"offlinerl"},{"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":"2201.09457","title":"Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity","created":"2022-01-24","cited_by_count":14,"area":null},{"id":"2110.11280","title":"Actor-critic is implicitly biased towards high entropy optimal policies","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2205.14211","title":"KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal","created":"2022-05-27","cited_by_count":13,"area":null},{"id":"2303.04386","title":"Policy Mirror Descent Inherently Explores Action Space","created":"2023-03-08","cited_by_count":13,"area":null},{"id":"2311.14168","title":"Fast Policy Learning for Linear Quadratic Control with Entropy Regularization","created":"2023-11-23","cited_by_count":13,"area":null},{"id":"2210.01282","title":"Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":12,"area":"offlinerl"},{"id":"2211.02105","title":"Geometry and convergence of natural policy gradient methods","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2407.17226","title":"Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems","created":"2024-07-24","cited_by_count":12,"area":"deeprl"},{"id":"2201.05756","title":"Block Policy Mirror Descent","created":"2022-01-15","cited_by_count":11,"area":null},{"id":"2405.10624","title":"Sample-Efficient Constrained Reinforcement Learning with General Parameterization","created":"2024-05-17","cited_by_count":11,"area":"deeprl"},{"id":"2204.05466","title":"Independent Natural Policy Gradient Methods for Potential Games: Finite-time Global Convergence with Entropy Regularization","created":"2022-04-12","cited_by_count":10,"area":null},{"id":"2307.09470","title":"Multi-Player Zero-Sum Markov Games with Networked Separable Interactions","created":"2023-07-13","cited_by_count":10,"area":null},{"id":"2405.19697","title":"Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity","created":"2024-05-30","cited_by_count":10,"area":"deeprl"},{"id":"2310.02671","title":"Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2310.08089","title":"Learning Regularized Monotone Graphon Mean-Field Games","created":"2023-10-12","cited_by_count":9,"area":null},{"id":"2410.05255","title":"Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization","created":"2024-10-07","cited_by_count":9,"area":"diffusion"},{"id":"2204.05176","title":"Towards Painless Policy Optimization for Constrained MDPs","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2210.12812","title":"Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergence","created":"2022-10-23","cited_by_count":8,"area":null},{"id":"2305.14608","title":"Inverse Reinforcement Learning with the Average Reward Criterion","created":"2023-05-24","cited_by_count":8,"area":"offlinerl"},{"id":"2405.18221","title":"Recurrent Natural Policy Gradient for POMDPs","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"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":"2301.10932","title":"On the Global Convergence of Risk-Averse Natural Policy Gradient Methods with Expected Conditional Risk Measures","created":"2023-01-26","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":"2410.15612","title":"In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory Terminates","created":"2024-10-21","cited_by_count":7,"area":"offlinerl"},{"id":"2306.14133","title":"Provably Convergent Policy Optimization via Metric-aware Trust Region Methods","created":"2023-06-25","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":"2401.17780","title":"A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees","created":"2024-01-31","cited_by_count":6,"area":"deeprl"},{"id":"2211.08980","title":"Asynchronous Gradient Play in Zero-Sum Multi-agent Games","created":"2022-11-16","cited_by_count":5,"area":null},{"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":"2403.19448","title":"Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients","created":"2024-03-28","cited_by_count":5,"area":"deeprl"},{"id":"2510.20235","title":"Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach","created":"2025-10-23","cited_by_count":5,"area":"deeprl"},{"id":"2109.11692","title":"Dimension-Free Rates for Natural Policy Gradient in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":4,"area":null},{"id":"2206.01666","title":"Algorithm for Constrained Markov Decision Process with Linear Convergence","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2305.06851","title":"Policy Gradient Algorithms Implicitly Optimize by Continuation","created":"2023-05-11","cited_by_count":4,"area":null},{"id":"2305.07248","title":"Quantile-Based Deep Reinforcement Learning using Two-Timescale Policy Gradient Algorithms","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2407.18143","title":"Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation","created":"2024-07-25","cited_by_count":4,"area":"deeprl"},{"id":"2502.07141","title":"Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2503.13538","title":"From Demonstrations to Rewards: Alignment Without Explicit Human Preferences","created":"2025-03-15","cited_by_count":4,"area":"alignment"}],"next_cursor":"100"}