{"total":100,"rows":[{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"area":null},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62,"area":null},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55,"area":null},{"id":"2111.05008","title":"Misspecified Gaussian Process Bandit Optimization","created":"2021-11-09","cited_by_count":55,"area":null},{"id":"2103.05324","title":"A Simple Approach for Non-stationary Linear Bandits","created":"2021-03-09","cited_by_count":54,"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":"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":"2104.03781","title":"Leveraging Good Representations in Linear Contextual Bandits","created":"2021-04-08","cited_by_count":29,"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":"2110.13282","title":"The Pareto Frontier of model selection for general Contextual Bandits","created":"2021-10-25","cited_by_count":24,"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":"2309.00814","title":"Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits","created":"2023-09-02","cited_by_count":19,"area":null},{"id":"2202.05100","title":"Adaptively Exploiting d-Separators with Causal Bandits","created":"2022-02-10","cited_by_count":18,"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":"2212.03798","title":"Stochastic Rising Bandits","created":"2022-12-07","cited_by_count":18,"area":null},{"id":"2106.05608","title":"Thompson Sampling with a Mixture Prior","created":"2021-06-10","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":"2102.06593","title":"Pareto Optimal Model Selection in Linear Bandits","created":"2021-02-12","cited_by_count":14,"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":"2111.00781","title":"Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure","created":"2021-11-01","cited_by_count":14,"area":null},{"id":"2211.02016","title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning","created":"2022-11-03","cited_by_count":13,"area":"offlinerl"},{"id":"2106.11935","title":"Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL","created":"2021-06-22","cited_by_count":12,"area":"offlinerl"},{"id":"2402.08672","title":"Model Assessment and Selection under Temporal Distribution Shift","created":"2024-02-13","cited_by_count":12,"area":null},{"id":"2112.12320","title":"Model Selection in Batch Policy Optimization","created":"2021-12-23","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":"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":"2402.01632","title":"Time-Varying Gaussian Process Bandits with Unknown Prior","created":"2024-02-02","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":"2106.02979","title":"Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms","created":"2021-06-05","cited_by_count":10,"area":null},{"id":"2202.07574","title":"Damped Online Newton Step for Portfolio Selection","created":"2022-02-15","cited_by_count":9,"area":null},{"id":"2207.11597","title":"Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference","created":"2022-07-23","cited_by_count":9,"area":null},{"id":"2107.03455","title":"Model Selection for Generic Contextual Bandits","created":"2021-07-07","cited_by_count":8,"area":null},{"id":"2110.14804","title":"Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers","created":"2021-10-27","cited_by_count":8,"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":"2203.04274","title":"Leveraging Initial Hints for Free in Stochastic Linear Bandits","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2301.10500","title":"Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning","created":"2023-01-25","cited_by_count":7,"area":null},{"id":"2410.10384","title":"Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal","created":"2024-10-14","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":"2512.23631","title":"BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2207.12805","title":"Neural Design for Genetic Perturbation Experiments","created":"2022-07-26","cited_by_count":6,"area":null},{"id":"2307.12897","title":"Anytime Model Selection in Linear Bandits","created":"2023-07-24","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":"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":"2410.13837","title":"ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization","created":"2024-10-17","cited_by_count":6,"area":"deeprl"},{"id":"2502.07064","title":"Contextual Thompson Sampling via Generation of Missing Data","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2106.05378","title":"Feature and Parameter Selection in Stochastic Linear Bandits","created":"2021-06-09","cited_by_count":5,"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":"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":"2304.13830","title":"Adaptation to Misspecified Kernel Regularity in Kernelised Bandits","created":"2023-04-26","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":"2405.14372","title":"Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints","created":"2024-05-23","cited_by_count":5,"area":"deeprl"},{"id":"2210.15513","title":"Lifelong Bandit Optimization: No Prior and No Regret","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2309.01730","title":"Adaptive Resource Allocation for Virtualized Base Stations in O-RAN with Online Learning","created":"2023-09-04","cited_by_count":4,"area":null},{"id":"2507.11891","title":"Choosing the Better Bandit Algorithm under Data Sharing: When Do A/B Experiments Work?","created":"2025-07-16","cited_by_count":4,"area":null},{"id":"2210.14998","title":"One Arrow, Two Kills: An Unified Framework for Achieving Optimal Regret Guarantees in Sleeping Bandits","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2607.09015","title":"Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing","created":"2026-07-10","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":"2210.13573","title":"Conditionally Risk-Averse Contextual Bandits","created":"2022-10-24","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":"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":"2407.00950","title":"Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals","created":"2024-07-01","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":"2511.10619","title":"Algorithm Design and Stronger Guarantees for the Improving Multi-Armed Bandits Problem","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2603.25916","title":"Parameter-Free Dynamic Regret for Unconstrained Linear Bandits","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2107.05849","title":"Model Selection for Generic Reinforcement Learning","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2110.13400","title":"Scale-Free Adversarial Multi-Armed Bandit with Arbitrary Feedback Delays","created":"2021-10-26","cited_by_count":1,"area":null},{"id":"2205.14839","title":"Adversarial Bandits against Arbitrary Strategies","created":"2022-05-30","cited_by_count":1,"area":null},{"id":"2207.02992","title":"Model Selection in Reinforcement Learning with General Function Approximations","created":"2022-07-06","cited_by_count":1,"area":null},{"id":"2302.09440","title":"Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Bandits","created":"2023-02-18","cited_by_count":1,"area":null},{"id":"2303.05018","title":"Improved Regret Bounds for Online Kernel Selection under Bandit Feedback","created":"2023-03-09","cited_by_count":1,"area":null},{"id":"2405.13899","title":"Symmetric Linear Bandits with Hidden Symmetry","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2408.08859","title":"Stochastic Bandits Robust to Adversarial Attacks","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2411.06069","title":"Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games","created":"2024-11-09","cited_by_count":1,"area":null},{"id":"2510.22654","title":"Managing Self-Learning Experts under Per-Round Budget Constraints","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2102.05164","title":"Nonstochastic Bandits with Infinitely Many Experts","created":"2021-02-09","cited_by_count":0,"area":null},{"id":"2106.02855","title":"Multi-armed Bandit Algorithms on System-on-Chip: Go Frequentist or Bayesian?","created":"2021-06-05","cited_by_count":0,"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":"2210.14077","title":"Eigen Memory Trees","created":"2022-10-25","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":"2302.09451","title":"Estimating Optimal Policy Value in General Linear Contextual Bandits","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2402.17720","title":"The SMART approach to instance-optimal online learning","created":"2024-02-27","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":"2408.04046","title":"Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives","created":"2024-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2410.20041","title":"Sparse Linear Bandits with Blocking Constraints","created":"2024-10-26","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":"2505.19061","title":"Hierarchical Adversarial Bandits for Online Configuration Optimization","created":"2025-05-25","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":"2602.17958","title":"Bayesian Online Model Selection","created":"2026-02-20","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":"2605.08558","title":"Beyond Static Bias: Adaptive Multi-Fidelity Bandits with Improving Proxies","created":"2026-05-08","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":"2609.06514","title":"Model-Adaptive and Risk-Constrained Frequency Hopping Against Predictive Jammers","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2610.02440","title":"Bandits via Additive Quantized Representations","created":"2026-10-01","cited_by_count":0,"area":"alignment"}],"next_cursor":null}