{"total":76,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2202.00817","title":"Do Differentiable Simulators Give Better Policy Gradients?","created":"2022-02-02","cited_by_count":89,"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":"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":"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":"2210.09921","title":"Finite-time analysis of single-timescale actor-critic","created":"2022-10-18","cited_by_count":32,"area":null},{"id":"2305.18901","title":"Policy Optimization for Continuous Reinforcement Learning","created":"2023-05-30","cited_by_count":31,"area":null},{"id":"2108.02731","title":"Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach","created":"2021-08-05","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":"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":"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":"2203.02591","title":"A Small Gain Analysis of Single Timescale Actor Critic","created":"2022-03-04","cited_by_count":24,"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":"2102.11866","title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality","created":"2021-02-23","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":"2206.05850","title":"Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm","created":"2022-06-12","cited_by_count":20,"area":null},{"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":"2110.15572","title":"Understanding the Effect of Stochasticity in Policy Optimization","created":"2021-10-29","cited_by_count":18,"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":"2106.12112","title":"Bregman Gradient Policy Optimization","created":"2021-06-23","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":"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":"2210.08857","title":"On the convergence of policy gradient methods to Nash equilibria in general stochastic games","created":"2022-10-17","cited_by_count":16,"area":null},{"id":"2101.01041","title":"Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity","created":"2021-01-04","cited_by_count":15,"area":null},{"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":"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":"2211.02105","title":"Geometry and convergence of natural policy gradient methods","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2201.12332","title":"On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces","created":"2022-01-28","cited_by_count":11,"area":null},{"id":"2102.10734","title":"Provable Super-Convergence with a Large Cyclical Learning Rate","created":"2021-02-22","cited_by_count":10,"area":null},{"id":"2206.06863","title":"How are policy gradient methods affected by the limits of control?","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2302.13144","title":"Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient","created":"2023-02-25","cited_by_count":10,"area":null},{"id":"2402.17235","title":"Stochastic Gradient Succeeds for Bandits","created":"2024-02-27","cited_by_count":10,"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":"2306.00324","title":"Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning","created":"2023-06-01","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":"2304.10951","title":"A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2310.19927","title":"Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2107.04422","title":"Policy Gradient Methods for Distortion Risk Measures","created":"2021-07-09","cited_by_count":6,"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":"2101.02137","title":"Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint","created":"2021-01-06","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":"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":"2206.06827","title":"Variance Reduction for Policy-Gradient Methods via Empirical Variance Minimization","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2208.08056","title":"Sampling Through the Lens of Sequential Decision Making","created":"2022-08-17","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":"2310.19022","title":"Optimization Landscape of Policy Gradient Methods for Discrete-time Static Output Feedback","created":"2023-10-29","cited_by_count":4,"area":null},{"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":"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":"2202.07496","title":"Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2202.11046","title":"A policy gradient approach for optimization of smooth risk measures","created":"2022-02-22","cited_by_count":2,"area":null},{"id":"2206.05652","title":"Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies","created":"2022-06-12","cited_by_count":2,"area":null},{"id":"2210.07651","title":"Decentralized Policy Gradient for Nash Equilibria Learning of General-sum Stochastic Games","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2303.12785","title":"Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality","created":"2023-03-22","cited_by_count":2,"area":null},{"id":"2311.07411","title":"A Large Deviations Perspective on Policy Gradient Algorithms","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2402.06388","title":"Convergence of a L2 regularized Policy Gradient Algorithm for the Multi Armed Bandit","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2502.11033","title":"Convergence of Policy Mirror Descent Beyond Compatible Function Approximation","created":"2025-02-16","cited_by_count":2,"area":null},{"id":"2607.22039","title":"Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs","created":"2026-07-24","cited_by_count":2,"area":null},{"id":"2105.13609","title":"A nearly Blackwell-optimal policy gradient method","created":"2021-05-28","cited_by_count":1,"area":null},{"id":"2110.12929","title":"Convergence Rates of Average-Reward Multi-agent Reinforcement Learning via Randomized Linear Programming","created":"2021-10-22","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":"2411.04913","title":"Structure Matters: Dynamic Policy Gradient","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2603.15001","title":"How Log-Barrier Helps Exploration in Policy Optimization","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2109.07054","title":"Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback","created":"2021-09-15","cited_by_count":0,"area":null},{"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":"2301.12174","title":"Stochastic Dimension-reduced Second-order Methods for Policy Optimization","created":"2023-01-28","cited_by_count":0,"area":null},{"id":"2412.14039","title":"Spatio-Temporal SIR Model of Pandemic Spread During Warfare with Optimal Dual-use Healthcare System Administration using Deep Reinforcement Learning","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2510.02735","title":"Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2605.03752","title":"Vanishing L2 regularization for the softmax Multi Armed Bandit","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2610.06861","title":"When Does External Guidance Help LLM Reasoning? A Bias-Variance Theory of Guidance-Augmented GRPO","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}