{"total":46,"rows":[{"id":"2102.05406","title":"Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach","created":"2021-02-10","cited_by_count":98,"area":null},{"id":"2112.14368","title":"Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization","created":"2021-12-29","cited_by_count":66,"area":null},{"id":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","cited_by_count":52,"area":null},{"id":"2102.05858","title":"Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously","created":"2021-02-11","cited_by_count":48,"area":null},{"id":"2110.03580","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","created":"2021-10-07","cited_by_count":45,"area":null},{"id":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"area":null},{"id":"2106.04117","title":"The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition","created":"2021-06-08","cited_by_count":40,"area":null},{"id":"2102.05800","title":"Robust Policy Gradient against Strong Data Corruption","created":"2021-02-11","cited_by_count":30,"area":null},{"id":"2103.13056","title":"Minimax Regret for Stochastic Shortest Path","created":"2021-03-24","cited_by_count":30,"area":null},{"id":"2302.09739","title":"A Blackbox Approach to Best of Both Worlds in Bandits and Beyond","created":"2023-02-20","cited_by_count":30,"area":null},{"id":"2102.05284","title":"Finding the Stochastic Shortest Path with Low Regret: The Adversarial Cost and Unknown Transition Case","created":"2021-02-10","cited_by_count":28,"area":null},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2206.08742","title":"Near-Optimal No-Regret Learning Dynamics for General Convex Games","created":"2022-06-17","cited_by_count":25,"area":null},{"id":"2106.08377","title":"Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path","created":"2021-06-15","cited_by_count":23,"area":null},{"id":"2102.06875","title":"Improved Corruption Robust Algorithms for Episodic Reinforcement Learning","created":"2021-02-13","cited_by_count":20,"area":null},{"id":"2305.00832","title":"First- and Second-Order Bounds for Adversarial Linear Contextual Bandits","created":"2023-05-01","cited_by_count":19,"area":null},{"id":"2309.00814","title":"Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits","created":"2023-09-02","cited_by_count":19,"area":null},{"id":"2302.09408","title":"Best of Both Worlds Policy Optimization","created":"2023-02-18","cited_by_count":17,"area":null},{"id":"2305.08629","title":"A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs","created":"2023-05-15","cited_by_count":15,"area":null},{"id":"2310.11550","title":"Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback","created":"2023-10-17","cited_by_count":13,"area":null},{"id":"2403.00715","title":"Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds","created":"2024-03-01","cited_by_count":11,"area":null},{"id":"2102.00490","title":"Online Markov Decision Processes with Aggregate Bandit Feedback","created":"2021-01-31","cited_by_count":10,"area":null},{"id":"2405.20678","title":"No-Regret Learning for Fair Multi-Agent Social Welfare Optimization","created":"2024-05-31","cited_by_count":8,"area":null},{"id":"2410.07533","title":"Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2307.12897","title":"Anytime Model Selection in Linear Bandits","created":"2023-07-24","cited_by_count":6,"area":null},{"id":"2404.09494","title":"On the Necessity of Collaboration for Online Model Selection with Decentralized Data","created":"2024-04-15","cited_by_count":6,"area":null},{"id":"2504.00461","title":"Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive Adversaries","created":"2025-04-01","cited_by_count":6,"area":null},{"id":"2210.01376","title":"Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2302.04374","title":"Near-Optimal Adversarial Reinforcement Learning with Switching Costs","created":"2023-02-08","cited_by_count":4,"area":null},{"id":"2508.01681","title":"Generalized Kernelized Bandits: A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2508.11931","title":"An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction","created":"2025-08-16","cited_by_count":4,"area":null},{"id":"2601.09825","title":"Eluder dimension: localise it!","created":"2026-01-14","cited_by_count":3,"area":null},{"id":"2202.06150","title":"Adaptive Bandit Convex Optimization with Heterogeneous Curvature","created":"2022-02-12","cited_by_count":2,"area":null},{"id":"2505.20010","title":"Data-Dependent Regret Bounds for Constrained MABs","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2505.20734","title":"Adversarial bandit optimization for approximately linear functions","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2312.01587","title":"Scalable and Independent Learning of Nash Equilibrium Policies in $n$-Player Stochastic Games with Unknown Independent Chains","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2405.02188","title":"Optimistic Regret Bounds for Online Learning in Adversarial Markov Decision Processes","created":"2024-05-03","cited_by_count":1,"area":null},{"id":"2603.26066","title":"Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2111.05486","title":"Uncoupled Bandit Learning towards Rationalizability: Benchmarks, Barriers, and Algorithms","created":"2021-11-10","cited_by_count":0,"area":null},{"id":"2405.06480","title":"Incentive-compatible Bandits: Importance Weighting No More","created":"2024-05-10","cited_by_count":0,"area":null},{"id":"2407.00916","title":"Learnability in Online Kernel Selection with Memory Constraint via Data-dependent Regret Analysis","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2602.09457","title":"From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.28201","title":"A Perturbation Approach to Unconstrained Linear Bandits","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.05129","title":"No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2608.15996","title":"Toward Optimal Second-Order Path-Length Guarantee for Adversarial Multi-Armed Bandits","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2610.17818","title":"Follow the Perturbed Leader for Linear Bandits: $\\sqrt{T}$ Regret over General Convex Sets","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}