{"total":105,"rows":[{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"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":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"area":null},{"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":"2107.02237","title":"Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination","created":"2021-07-05","cited_by_count":53,"area":null},{"id":"2202.04690","title":"Smoothed Online Learning is as Easy as Statistical Learning","created":"2022-02-09","cited_by_count":52,"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":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"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":"2307.03848","title":"Optimal Learners for Realizable Regression: PAC Learning and Online Learning","created":"2023-07-07","cited_by_count":23,"area":null},{"id":"2204.00043","title":"Efficient Active Learning with Abstention","created":"2022-03-31","cited_by_count":22,"area":null},{"id":"2404.06831","title":"Generalized Linear Bandits with Limited Adaptivity","created":"2024-04-10","cited_by_count":22,"area":null},{"id":"2102.13240","title":"Adapting to Misspecification in Contextual Bandits with Offline Regression Oracles","created":"2021-02-26","cited_by_count":21,"area":null},{"id":"2202.08549","title":"Oracle-Efficient Online Learning for Beyond Worst-Case Adversaries","created":"2022-02-17","cited_by_count":21,"area":null},{"id":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"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":"2406.02611","title":"LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments","created":"2024-06-03","cited_by_count":18,"area":null},{"id":"2205.10895","title":"Contextual Information-Directed Sampling","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2207.02357","title":"Instance-optimal PAC Algorithms for Contextual Bandits","created":"2022-07-05","cited_by_count":16,"area":null},{"id":"2406.12125","title":"Efficient Sequential Decision Making with Large Language Models","created":"2024-06-17","cited_by_count":16,"area":null},{"id":"2106.14979","title":"On component interactions in two-stage recommender systems","created":"2021-06-28","cited_by_count":14,"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":"2207.11126","title":"Optimism in Face of a Context: Regret Guarantees for Stochastic Contextual MDP","created":"2022-07-22","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":"2106.01723","title":"Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning","created":"2021-06-03","cited_by_count":10,"area":null},{"id":"2203.00995","title":"Learning Efficiently Function Approximation for Contextual MDP","created":"2022-03-02","cited_by_count":10,"area":null},{"id":"2307.05341","title":"Tracking Most Significant Shifts in Nonparametric Contextual Bandits","created":"2023-07-11","cited_by_count":10,"area":null},{"id":"2211.14932","title":"Eluder-based Regret for Stochastic Contextual MDPs","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2303.01464","title":"Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation","created":"2023-03-02","cited_by_count":9,"area":null},{"id":"2410.12713","title":"How Does Variance Shape the Regret in Contextual Bandits?","created":"2024-10-16","cited_by_count":9,"area":null},{"id":"2102.07800","title":"Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2107.03455","title":"Model Selection for Generic Contextual Bandits","created":"2021-07-07","cited_by_count":8,"area":null},{"id":"2405.17796","title":"Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2211.12004","title":"Contextual Bandits in a Survey Experiment on Charitable Giving: Within-Experiment Outcomes versus Policy Learning","created":"2022-11-22","cited_by_count":7,"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":"2303.04845","title":"Smoothed Analysis of Sequential Probability Assignment","created":"2023-03-08","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":"2302.12120","title":"Sequential Counterfactual Risk Minimization","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2402.08127","title":"Efficient Contextual Bandits with Uninformed Feedback Graphs","created":"2024-02-12","cited_by_count":6,"area":null},{"id":"2405.06575","title":"No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization","created":"2024-05-10","cited_by_count":6,"area":null},{"id":"2506.12751","title":"Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions","created":"2025-06-15","cited_by_count":6,"area":null},{"id":"2106.06483","title":"Towards Costless Model Selection in Contextual Bandits: A Bias-Variance Perspective","created":"2021-06-11","cited_by_count":5,"area":null},{"id":"2111.04688","title":"Universal and data-adaptive algorithms for model selection in linear contextual bandits","created":"2021-11-08","cited_by_count":5,"area":null},{"id":"2204.11910","title":"Integrating Reward Maximization and Population Estimation: Sequential Decision-Making for Internal Revenue Service Audit Selection","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2205.09899","title":"Breaking the $\\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits","created":"2022-05-19","cited_by_count":5,"area":null},{"id":"2210.13083","title":"Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2401.05193","title":"Experiment Planning with Function Approximation","created":"2024-01-10","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":"2106.13539","title":"Dealing with Expert Bias in Collective Decision-Making","created":"2021-06-25","cited_by_count":4,"area":null},{"id":"2306.13053","title":"Context-lumpable stochastic bandits","created":"2023-06-22","cited_by_count":4,"area":null},{"id":"2310.05047","title":"Online Learning in Contextual Second-Price Pay-Per-Click Auctions","created":"2023-10-08","cited_by_count":4,"area":null},{"id":"2402.08126","title":"Contextual Multinomial Logit Bandits with General Value Functions","created":"2024-02-12","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":"2405.20677","title":"Provably Efficient Interactive-Grounded Learning with Personalized Reward","created":"2024-05-31","cited_by_count":3,"area":null},{"id":"2406.11667","title":"Is Efficient PAC Learning Possible with an Oracle That Responds 'Yes' or 'No'?","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2501.14155","title":"Learning to Price with Resource Constraints: From Full Information to Machine-Learned Prices","created":"2025-01-24","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":"2210.13573","title":"Conditionally Risk-Averse Contextual Bandits","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2212.09429","title":"On the Complexity of Representation Learning in Contextual Linear Bandits","created":"2022-12-19","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":"2303.10218","title":"An Empirical Evaluation of Federated Contextual Bandit Algorithms","created":"2023-03-17","cited_by_count":2,"area":null},{"id":"2310.19025","title":"An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits","created":"2023-10-29","cited_by_count":2,"area":null},{"id":"2404.09413","title":"On the Optimal Regret of Locally Private Linear Contextual Bandit","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2410.11227","title":"Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2501.06339","title":"On The Statistical Complexity of Offline Decision-Making","created":"2025-01-10","cited_by_count":2,"area":null},{"id":"2503.03023","title":"Quantum Non-Linear Bandit Optimization","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2503.04010","title":"Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2506.00135","title":"Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2602.13700","title":"Optimal Regret for Policy Optimization in Contextual Bandits","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2602.13706","title":"Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2308.15107","title":"Stochastic Graph Bandit Learning with Side-Observations","created":"2023-08-29","cited_by_count":1,"area":null},{"id":"2312.03253","title":"Seller-side Outcome Fairness in Online Marketplaces","created":"2023-12-06","cited_by_count":1,"area":null},{"id":"2312.16341","title":"Harnessing the Power of Federated Learning in Federated Contextual Bandits","created":"2023-12-26","cited_by_count":1,"area":null},{"id":"2406.04374","title":"Incentivized Exploration with Stochastic Covariates: A Two-Stage Mechanism Design for Recommender System","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2411.11794","title":"Competing Bandits in Decentralized Contextual Matching Markets","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2505.07101","title":"Constrained Online Decision-Making: A Unified Framework","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2605.07155","title":"Regret-Oracle Complexity Tradeoffs in Agnostic Online Learning","created":"2026-05-08","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":"2609.13564","title":"When Greedy Sampling Explores: KL-Regularized Contextual Bandits without Eluder-Dimension Dependence","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2107.03263","title":"Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodes","created":"2021-07-07","cited_by_count":0,"area":null},{"id":"2209.03224","title":"Dual Instrumental Method for Confounded Kernelized Bandits","created":"2022-09-07","cited_by_count":0,"area":null},{"id":"2304.13033","title":"SmartChoices: Augmenting Software with Learned Implementations","created":"2023-04-12","cited_by_count":0,"area":null},{"id":"2310.02246","title":"Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2310.16096","title":"Contextual Bandits for Evaluating and Improving Inventory Control Policies","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2404.13391","title":"Online Planning of Power Flows for Power Systems Against Bushfires Using Spatial Context","created":"2024-04-20","cited_by_count":0,"area":null},{"id":"2405.04636","title":"Data-driven Error Estimation: Excess Risk Bounds without Class Complexity as Input","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2502.05145","title":"From Restless to Contextual: A Thresholding Bandit Reformulation For Finite-horizon Improvement","created":"2025-02-07","cited_by_count":0,"area":null},{"id":"2505.16829","title":"Contextual Learning for Stochastic Optimization","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2505.16918","title":"Scalable and Interpretable Contextual Bandits: A Literature Review and Retail Offer Prototype","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2509.05864","title":"Beyond ATE: Multi-Criteria Design for A/B Testing","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2509.07633","title":"Variational Quantum Circuits in Offline Contextual Bandit Problems","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2510.15483","title":"Fast Best-in-Class Regret for Contextual Bandits","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.17390","title":"Exploration via Feature Perturbation in Contextual Bandits","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2512.21794","title":"Multi-agent Adaptive Mechanism Design","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2601.06913","title":"Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities","created":"2026-01-11","cited_by_count":0,"area":null}],"next_cursor":"100"}