{"total":197,"rows":[{"id":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178,"area":null},{"id":"2110.04652","title":"Representation Learning for Online and Offline RL in Low-rank MDPs","created":"2021-10-09","cited_by_count":129,"area":"offlinerl"},{"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":"2111.05008","title":"Misspecified Gaussian Process Bandit Optimization","created":"2021-11-09","cited_by_count":55,"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":"2106.02757","title":"Heuristic-Guided Reinforcement Learning","created":"2021-06-05","cited_by_count":42,"area":null},{"id":"2103.12690","title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap","created":"2021-03-23","cited_by_count":40,"area":null},{"id":"2307.08999","title":"Oracle Efficient Online Multicalibration and Omniprediction","created":"2023-07-18","cited_by_count":37,"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":"2301.13767","title":"Multicalibration as Boosting for Regression","created":"2023-01-31","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":"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":"2211.07627","title":"Redeeming Intrinsic Rewards via Constrained Optimization","created":"2022-11-14","cited_by_count":24,"area":null},{"id":"2310.18554","title":"Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion","created":"2023-10-28","cited_by_count":24,"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":"2402.07198","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","created":"2024-02-11","cited_by_count":23,"area":"offlinerl"},{"id":"2109.07340","title":"Distribution-free Contextual Dynamic Pricing","created":"2021-09-15","cited_by_count":22,"area":null},{"id":"2204.00043","title":"Efficient Active Learning with Abstention","created":"2022-03-31","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":"2202.10066","title":"Multi-task Representation Learning with Stochastic Linear Bandits","created":"2022-02-21","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":"2205.15372","title":"Optimistic Whittle Index Policy: Online Learning for Restless Bandits","created":"2022-05-30","cited_by_count":20,"area":null},{"id":"2205.13924","title":"Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits","created":"2022-05-27","cited_by_count":19,"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":"2102.01729","title":"Majorizing Measures, Sequential Complexities, and Online Learning","created":"2021-02-02","cited_by_count":17,"area":null},{"id":"2111.08911","title":"Fast Rates for Nonparametric Online Learning: From Realizability to Learning in Games","created":"2021-11-17","cited_by_count":16,"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":"2302.02552","title":"Adapting to Continuous Covariate Shift via Online Density Ratio Estimation","created":"2023-02-06","cited_by_count":15,"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":"2402.14987","title":"On the Performance of Empirical Risk Minimization with Smoothed Data","created":"2024-02-22","cited_by_count":13,"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":"2410.05117","title":"Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability","created":"2024-10-07","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":"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":"2312.15433","title":"Best-of-Both-Worlds Algorithms for Linear Contextual Bandits","created":"2023-12-24","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":"2205.13056","title":"Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions","created":"2022-05-25","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":"2312.14037","title":"Neural Contextual Bandits for Personalized Recommendation","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2404.12522","title":"Neural Active Learning Beyond Bandits","created":"2024-04-18","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":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2409.16197","title":"Second Order Bounds for Contextual Bandits with Function Approximation","created":"2024-09-24","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":"2407.07596","title":"Learning treatment effects while treating those in need","created":"2024-07-10","cited_by_count":8,"area":null},{"id":"2506.12721","title":"Strategic Scaling of Test-Time Compute: A Bandit Learning Approach","created":"2025-06-15","cited_by_count":8,"area":"lr"},{"id":"2107.02377","title":"A Short Note on the Relationship of Information Gain and Eluder Dimension","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2202.02407","title":"An Experimental Design Approach for Regret Minimization in Logistic Bandits","created":"2022-02-04","cited_by_count":7,"area":null},{"id":"2206.02326","title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2210.09385","title":"Adaptive Oracle-Efficient Online Learning","created":"2022-10-17","cited_by_count":7,"area":null},{"id":"2211.09100","title":"Global Optimization with Parametric Function Approximation","created":"2022-11-16","cited_by_count":7,"area":null},{"id":"2211.16110","title":"PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison","created":"2022-11-29","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":"2302.09357","title":"Stochastic Online Instrumental Variable Regression: Regrets for Endogeneity and Bandit Feedback","created":"2023-02-18","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":"2305.03784","title":"Neural Exploitation and Exploration of Contextual Bandits","created":"2023-05-05","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":"2402.15411","title":"Optimistic Information Directed Sampling","created":"2024-02-23","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":"2502.01118","title":"Large Language Model-Enhanced Multi-Armed Bandits","created":"2025-02-03","cited_by_count":7,"area":null},{"id":"2109.05546","title":"Improved Algorithms for Misspecified Linear Markov Decision Processes","created":"2021-09-12","cited_by_count":6,"area":null},{"id":"2302.12120","title":"Sequential Counterfactual Risk Minimization","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2307.10167","title":"VITS : Variational Inference Thompson Sampling for contextual bandits","created":"2023-07-19","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":"2402.08127","title":"Efficient Contextual Bandits with Uninformed Feedback Graphs","created":"2024-02-12","cited_by_count":6,"area":null},{"id":"2402.09483","title":"Oracle-Efficient Differentially Private Learning with Public Data","created":"2024-02-13","cited_by_count":6,"area":null},{"id":"2404.03774","title":"Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning","created":"2024-04-04","cited_by_count":6,"area":"deeprl"},{"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":"2601.22538","title":"Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Models","created":"2026-01-30","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":"2109.10935","title":"Robust Generalization of Quadratic Neural Networks via Function Identification","created":"2021-09-22","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":"2205.13114","title":"Contextual Pandora's Box","created":"2022-05-26","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":"2304.13593","title":"Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards","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":"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":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"}],"next_cursor":"100"}