{"total":122,"rows":[{"id":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96,"area":null},{"id":"2102.06548","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","created":"2021-02-12","cited_by_count":92,"area":null},{"id":"2211.07937","title":"An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods","created":"2022-11-15","cited_by_count":68,"area":null},{"id":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60,"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":"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":"2101.08862","title":"Breaking the Deadly Triad with a Target Network","created":"2021-01-21","cited_by_count":47,"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":"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":"2210.09921","title":"Finite-time analysis of single-timescale actor-critic","created":"2022-10-18","cited_by_count":32,"area":null},{"id":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"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":"2109.03699","title":"Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis","created":"2021-09-08","cited_by_count":26,"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":"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":"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":"2109.14756","title":"A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning","created":"2021-09-29","cited_by_count":24,"area":null},{"id":"2203.02591","title":"A Small Gain Analysis of Single Timescale Actor Critic","created":"2022-03-04","cited_by_count":24,"area":null},{"id":"2509.11452","title":"Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting","created":"2025-09-14","cited_by_count":23,"area":"alignment"},{"id":"2010.08920","title":"Average-reward model-free reinforcement learning: a systematic review and literature mapping","created":"2020-10-18","cited_by_count":22,"area":"alignment"},{"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":"2106.13781","title":"Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems","created":"2021-06-25","cited_by_count":22,"area":null},{"id":"2102.11866","title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality","created":"2021-02-23","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":"2208.11639","title":"Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path","created":"2022-08-24","cited_by_count":20,"area":null},{"id":"2301.12083","title":"Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic","created":"2023-01-28","cited_by_count":18,"area":null},{"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,"area":null},{"id":"2111.02997","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","created":"2021-11-04","cited_by_count":17,"area":null},{"id":"2206.10414","title":"A Single-Timescale Analysis For Stochastic Approximation With Multiple Coupled Sequences","created":"2022-06-21","cited_by_count":17,"area":null},{"id":"2305.19001","title":"High-probability sample complexities for policy evaluation with linear function approximation","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2202.06828","title":"On the Convergence of SARSA with Linear Function Approximation","created":"2022-02-14","cited_by_count":15,"area":null},{"id":"2207.02829","title":"Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods","created":"2022-07-06","cited_by_count":15,"area":null},{"id":"2303.03100","title":"A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games","created":"2023-03-03","cited_by_count":15,"area":null},{"id":"2407.18878","title":"A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach","created":"2024-07-26","cited_by_count":15,"area":"deeprl"},{"id":"2106.07472","title":"Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation","created":"2021-06-14","cited_by_count":14,"area":null},{"id":"2202.00048","title":"Single Time-scale Actor-critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees","created":"2022-01-31","cited_by_count":14,"area":null},{"id":"2210.12624","title":"Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach","created":"2022-10-23","cited_by_count":14,"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":"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":"2501.19254","title":"Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set","created":"2025-01-31","cited_by_count":12,"area":"deeprl"},{"id":"2104.01627","title":"Finite-Time Convergence Rates of Nonlinear Two-Time-Scale Stochastic Approximation under Markovian Noise","created":"2021-04-04","cited_by_count":10,"area":null},{"id":"2302.05816","title":"A Policy Gradient Framework for Stochastic Optimal Control Problems with Global Convergence Guarantee","created":"2023-02-11","cited_by_count":10,"area":null},{"id":"2405.09660","title":"Fast Two-Time-Scale Stochastic Gradient Method with Applications in Reinforcement Learning","created":"2024-05-15","cited_by_count":10,"area":"deeprl"},{"id":"2409.19546","title":"Asymptotic and Finite Sample Analysis of Nonexpansive Stochastic Approximations with Markovian Noise","created":"2024-09-29","cited_by_count":10,"area":null},{"id":"2206.12848","title":"Analysis of Stochastic Processes through Replay Buffers","created":"2022-06-26","cited_by_count":9,"area":null},{"id":"2104.02836","title":"Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation","created":"2021-04-07","cited_by_count":8,"area":null},{"id":"2208.08744","title":"Global Convergence of Two-timescale Actor-Critic for Solving Linear Quadratic Regulator","created":"2022-08-18","cited_by_count":8,"area":null},{"id":"2210.04527","title":"A policy gradient approach for Finite Horizon Constrained Markov Decision Processes","created":"2022-10-10","cited_by_count":8,"area":null},{"id":"2103.16377","title":"Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity","created":"2021-03-30","cited_by_count":7,"area":null},{"id":"2110.00445","title":"Sim and Real: Better Together","created":"2021-10-01","cited_by_count":7,"area":null},{"id":"2112.13530","title":"Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic","created":"2021-12-27","cited_by_count":7,"area":null},{"id":"2201.10447","title":"Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization","created":"2022-01-25","cited_by_count":7,"area":null},{"id":"2308.01481","title":"Online covariance estimation for stochastic gradient descent under Markovian sampling","created":"2023-08-03","cited_by_count":7,"area":null},{"id":"2401.12764","title":"Fast Nonlinear Two-Time-Scale Stochastic Approximation: Achieving $O(1/k)$ Finite-Sample Complexity","created":"2024-01-23","cited_by_count":7,"area":null},{"id":"2402.01147","title":"Efficient Reinforcement Learning for Routing Jobs in Heterogeneous Queueing Systems","created":"2024-02-02","cited_by_count":7,"area":"deeprl"},{"id":"2402.01371","title":"Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation","created":"2024-02-02","cited_by_count":7,"area":null},{"id":"2110.05597","title":"Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees","created":"2021-10-11","cited_by_count":6,"area":null},{"id":"2502.09884","title":"Nonasymptotic CLT and Error Bounds for Linear Two-Time-Scale Stochastic Approximation","created":"2025-02-14","cited_by_count":6,"area":null},{"id":"2106.00993","title":"On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction","created":"2021-06-02","cited_by_count":5,"area":null},{"id":"2204.00006","title":"Data Sampling Affects the Complexity of Online SGD over Dependent Data","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2306.10486","title":"On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization","created":"2023-06-18","cited_by_count":5,"area":null},{"id":"2311.02546","title":"On the Second-Order Convergence of Biased Policy Gradient Algorithms","created":"2023-11-05","cited_by_count":5,"area":null},{"id":"2409.12135","title":"Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features","created":"2024-09-18","cited_by_count":5,"area":"deeprl"},{"id":"2505.21391","title":"Finite Sample Analysis of Linear Temporal Difference Learning with Arbitrary Features","created":"2025-05-27","cited_by_count":5,"area":"deeprl"},{"id":"2510.08539","title":"On the optimization dynamics of RLVR: Gradient gap and step size thresholds","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2510.16132","title":"A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies","created":"2025-10-17","cited_by_count":4,"area":"deeprl"},{"id":"2208.03247","title":"An Approximate Policy Iteration Viewpoint of Actor-Critic Algorithms","created":"2022-08-05","cited_by_count":3,"area":null},{"id":"2211.07675","title":"On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2303.12981","title":"Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2305.15249","title":"Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2408.04780","title":"Learning in Herding Mean Field Games: Single-Loop Algorithm with Finite-Time Convergence Analysis","created":"2024-08-08","cited_by_count":3,"area":"deeprl"},{"id":"2410.08868","title":"On the Convergence of Single-Timescale Actor-Critic","created":"2024-10-11","cited_by_count":3,"area":"deeprl"},{"id":"2410.15610","title":"On The Global Convergence Of Online RLHF With Neural Parametrization","created":"2024-10-21","cited_by_count":3,"area":"alignment"},{"id":"2501.10806","title":"Non-Expansive Mappings in Two-Time-Scale Stochastic Approximation: Finite-Time Analysis","created":"2025-01-18","cited_by_count":3,"area":"deeprl"},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2108.08655","title":"Global Convergence of the ODE Limit for Online Actor-Critic Algorithms in Reinforcement Learning","created":"2021-08-19","cited_by_count":2,"area":null},{"id":"2110.08902","title":"On the Convergence of Experience Replay in Policy Optimization: Characterizing Bias, Variance, and Finite-Time Convergence","created":"2021-10-17","cited_by_count":2,"area":null},{"id":"2206.06995","title":"Two-Timescale Stochastic Approximation for Bilevel Optimisation Problems in Continuous-Time Models","created":"2022-06-14","cited_by_count":2,"area":null},{"id":"2211.04088","title":"A Penalty-Based Method for Communication-Efficient Decentralized Bilevel Programming","created":"2022-11-08","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":"2310.16363","title":"Finite-Time Analysis of Three-Timescale Constrained Actor-Critic and Constrained Natural Actor-Critic Algorithms","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2312.08008","title":"Learning in Zero-Sum Markov Games: Relaxing Strong Reachability and Mixing Time Assumptions","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2401.15196","title":"Regularized Q-Learning with Linear Function Approximation","created":"2024-01-26","cited_by_count":2,"area":"deeprl"},{"id":"2410.09728","title":"Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator","created":"2024-10-13","cited_by_count":2,"area":"deeprl"},{"id":"2505.01041","title":"Global Optimality of Single-Timescale Actor-Critic under Continuous State-Action Space: A Study on Linear Quadratic Regulator","created":"2025-05-02","cited_by_count":2,"area":"deeprl"},{"id":"2510.12334","title":"Finite-time Convergence Analysis of Actor-Critic with Evolving Reward","created":"2025-10-14","cited_by_count":2,"area":"deeprl"},{"id":"2512.17688","title":"Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous Agents","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2512.24056","title":"Policy Mirror Descent with Temporal Difference Learning: Sample Complexity under Online Markov Data","created":"2025-12-30","cited_by_count":2,"area":"deeprl"},{"id":"2602.16629","title":"Almost Sure Convergence of Differential Temporal Difference Learning for Average Reward Markov Decision Processes","created":"2026-02-18","cited_by_count":2,"area":"deeprl"},{"id":"2111.12665","title":"Finite-Time Error Bounds for Distributed Linear Stochastic Approximation","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2202.13863","title":"Provably Efficient Convergence of Primal-Dual Actor-Critic with Nonlinear Function Approximation","created":"2022-02-28","cited_by_count":1,"area":null},{"id":"2206.05733","title":"Finite-Time Analysis of Fully Decentralized Single-Timescale Actor-Critic","created":"2022-06-12","cited_by_count":1,"area":null},{"id":"2208.12341","title":"Variance Reduction based Experience Replay for Policy Optimization","created":"2022-08-25","cited_by_count":1,"area":null},{"id":"2406.01838","title":"Learning the Target Network in Function Space","created":"2024-06-03","cited_by_count":1,"area":"deeprl"},{"id":"2411.14117","title":"Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problems","created":"2024-11-21","cited_by_count":1,"area":"deeprl"},{"id":"2503.17865","title":"Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality","created":"2025-03-22","cited_by_count":1,"area":"offlinerl"},{"id":"2504.17356","title":"Comprehend, Divide, and Conquer: Feature Subspace Exploration via Multi-Agent Hierarchical Reinforcement Learning","created":"2025-04-24","cited_by_count":1,"area":"agents"},{"id":"2509.13628","title":"Accelerated Gradient Methods with Biased Gradient Estimates: Risk Sensitivity, High-Probability Guarantees, and Large Deviation Bounds","created":"2025-09-17","cited_by_count":1,"area":null}],"next_cursor":"100"}