{"total":81,"rows":[{"id":"2110.00871","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","created":"2021-10-02","cited_by_count":66,"area":null},{"id":"2111.05008","title":"Misspecified Gaussian Process Bandit Optimization","created":"2021-11-09","cited_by_count":55,"area":null},{"id":"2205.06811","title":"Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions","created":"2022-05-13","cited_by_count":51,"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":"2111.12306","title":"Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability","created":"2021-11-24","cited_by_count":44,"area":null},{"id":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"area":null},{"id":"2212.05949","title":"Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes","created":"2022-12-12","cited_by_count":33,"area":null},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2211.07484","title":"Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression","created":"2022-11-14","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":"2210.12496","title":"Bayesian Optimization with Conformal Prediction Sets","created":"2022-10-22","cited_by_count":28,"area":null},{"id":"2108.06422","title":"Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models","created":"2021-08-13","cited_by_count":24,"area":null},{"id":"2110.13282","title":"The Pareto Frontier of model selection for general Contextual Bandits","created":"2021-10-25","cited_by_count":24,"area":null},{"id":"2109.07340","title":"Distribution-free Contextual Dynamic Pricing","created":"2021-09-15","cited_by_count":22,"area":null},{"id":"2202.06151","title":"Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits","created":"2022-02-12","cited_by_count":22,"area":null},{"id":"2110.12615","title":"Linear Contextual Bandits with Adversarial Corruptions","created":"2021-10-25","cited_by_count":21,"area":null},{"id":"2211.05632","title":"Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithms","created":"2022-11-08","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":"2207.05849","title":"Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces","created":"2022-07-12","cited_by_count":18,"area":null},{"id":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","cited_by_count":18,"area":null},{"id":"2202.02765","title":"Pushing the Efficiency-Regret Pareto Frontier for Online Learning of Portfolios and Quantum States","created":"2022-02-06","cited_by_count":15,"area":null},{"id":"2302.12370","title":"Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds","created":"2023-02-24","cited_by_count":14,"area":null},{"id":"2402.01096","title":"Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance","created":"2024-02-02","cited_by_count":14,"area":null},{"id":"2111.01479","title":"Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification","created":"2021-11-02","cited_by_count":12,"area":null},{"id":"2210.11834","title":"Optimal Contextual Bandits with Knapsacks under Realizability via Regression Oracles","created":"2022-10-21","cited_by_count":12,"area":null},{"id":"2310.02717","title":"Online Clustering of Bandits with Misspecified User Models","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2202.13227","title":"Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework","created":"2022-02-26","cited_by_count":11,"area":null},{"id":"2206.14912","title":"Best of Both Worlds Model Selection","created":"2022-06-29","cited_by_count":11,"area":null},{"id":"2302.08631","title":"Practical Contextual Bandits with Feedback Graphs","created":"2023-02-17","cited_by_count":11,"area":null},{"id":"2306.02869","title":"Data-Driven Online Model Selection With Regret Guarantees","created":"2023-06-05","cited_by_count":11,"area":null},{"id":"2312.15433","title":"Best-of-Both-Worlds Algorithms for Linear Contextual Bandits","created":"2023-12-24","cited_by_count":11,"area":null},{"id":"2202.07574","title":"Damped Online Newton Step for Portfolio Selection","created":"2022-02-15","cited_by_count":9,"area":null},{"id":"2302.06025","title":"Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits","created":"2023-02-12","cited_by_count":7,"area":null},{"id":"2306.10694","title":"On the Model-Misspecification in Reinforcement Learning","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2307.02108","title":"Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2405.10027","title":"The Real Price of Bandit Information in Multiclass Classification","created":"2024-05-16","cited_by_count":7,"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":"2501.02926","title":"Offline-to-online hyperparameter transfer for stochastic bandits","created":"2025-01-06","cited_by_count":7,"area":"offlinerl"},{"id":"2109.05546","title":"Improved Algorithms for Misspecified Linear Markov Decision Processes","created":"2021-09-12","cited_by_count":6,"area":null},{"id":"2303.09390","title":"On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits","created":"2023-03-16","cited_by_count":6,"area":null},{"id":"2310.01609","title":"Adversarial Contextual Bandits Go Kernelized","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2402.10028","title":"Diffusion Models Meet Contextual Bandits","created":"2024-02-15","cited_by_count":5,"area":"diffusion"},{"id":"2402.10289","title":"Thompson Sampling in Partially Observable Contextual Bandits","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2506.11831","title":"Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2510.09127","title":"Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2601.15353","title":"Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions","created":"2026-01-21","cited_by_count":5,"area":"deeprl"},{"id":"2210.14483","title":"Robust Contextual Linear Bandits","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2210.15513","title":"Lifelong Bandit Optimization: No Prior and No Regret","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2310.19794","title":"Robust Causal Bandits for Linear Models","created":"2023-10-30","cited_by_count":4,"area":null},{"id":"2602.08372","title":"Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2602.09456","title":"Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2605.09363","title":"Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions","created":"2026-05-10","cited_by_count":4,"area":"alignment"},{"id":"2605.26156","title":"Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2303.16998","title":"Does Sparsity Help in Learning Misspecified Linear Bandits?","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2507.07852","title":"Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2606.06053","title":"Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification","created":"2026-06-04","cited_by_count":3,"area":"deeprl"},{"id":"2210.13573","title":"Conditionally Risk-Averse Contextual Bandits","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2210.13625","title":"Deploying a Steered Query Optimizer in Production at Microsoft","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2301.11461","title":"Learning to Generate All Feasible Actions","created":"2023-01-26","cited_by_count":2,"area":null},{"id":"2302.08551","title":"Infinite Action Contextual Bandits with Reusable Data Exhaust","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2302.13252","title":"No-Regret Linear Bandits beyond Realizability","created":"2023-02-26","cited_by_count":2,"area":null},{"id":"2309.16563","title":"CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2405.07795","title":"Improved Bound for Robust Causal Bandits with Linear Models","created":"2024-05-13","cited_by_count":2,"area":null},{"id":"2508.18768","title":"Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits","created":"2025-08-26","cited_by_count":2,"area":null},{"id":"2203.16668","title":"Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oracles","created":"2022-03-30","cited_by_count":1,"area":"alignment"},{"id":"2405.13899","title":"Symmetric Linear Bandits with Hidden Symmetry","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2602.10971","title":"A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2604.24016","title":"Direction-Aware Offline-to-Online Learning in Linear Contextual Bandits","created":"2026-04-27","cited_by_count":1,"area":"offlinerl"},{"id":"2606.14929","title":"Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.13686","title":"Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2201.01973","title":"Robust Linear Predictions: Analyses of Uniform Concentration, Fast Rates and Model Misspecification","created":"2022-01-06","cited_by_count":0,"area":null},{"id":"2302.03784","title":"Leveraging User-Triggered Supervision in Contextual Bandits","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2503.16382","title":"Sparse Nonparametric Contextual Bandits","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2509.01924","title":"Non-Linear Model-Based Sequential Decision-Making in Agriculture","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2510.27177","title":"A Polynomial-time Algorithm for Online Sparse Linear Regression with Improved Regret Bound under Weaker Conditions","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2512.02214","title":"Improved Training Mechanism for Reinforcement Learning via Online Model Selection","created":"2025-12-01","cited_by_count":0,"area":"deeprl"},{"id":"2512.12693","title":"Co-Exploration and Co-Exploitation via Shared Structure in Multi-Task Bandits","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2603.12530","title":"Mixing Makes Markovian Contexts Cheap for Linear Bandits","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2606.27917","title":"Graph Dimensionality Reduction for Contextual Bandits: Structure-Specific Regret Bounds under Approximate Smoothness and Noisy Eigenspaces","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.02891","title":"Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2609.38659","title":"Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivity","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}