{"total":201,"rows":[{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223,"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":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104,"area":"synth"},{"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":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83,"area":"offlinerl"},{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"area":null},{"id":"1905.10948","title":"Provably Efficient Imitation Learning from Observation Alone","created":"2019-05-27","cited_by_count":78,"area":"offlinerl"},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53,"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":"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":"2108.08993","title":"Distributionally Robust Learning","created":"2021-08-20","cited_by_count":44,"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":"2510.27280","title":"FOCUS: Efficient Keyframe Selection for Long Video Understanding","created":"2025-10-31","cited_by_count":37,"area":"mllm"},{"id":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"area":null},{"id":"2210.01745","title":"Making Decisions under Outcome Performativity","created":"2022-10-04","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":"2209.15634","title":"A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning","created":"2022-09-30","cited_by_count":31,"area":null},{"id":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30,"area":"lr"},{"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":"2302.06606","title":"Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation","created":"2023-02-13","cited_by_count":30,"area":null},{"id":"2110.08847","title":"Provable RL with Exogenous Distractors via Multistep Inverse Dynamics","created":"2021-10-17","cited_by_count":28,"area":null},{"id":"2201.06532","title":"A New Look at Dynamic Regret for Non-Stationary Stochastic Bandits","created":"2022-01-17","cited_by_count":28,"area":null},{"id":"2202.01752","title":"Near-Optimal Learning of Extensive-Form Games with Imperfect Information","created":"2022-02-03","cited_by_count":26,"area":null},{"id":"2111.13807","title":"Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization","created":"2021-11-27","cited_by_count":25,"area":"offlinerl"},{"id":"2102.10221","title":"Logarithmic Regret in Feature-based Dynamic Pricing","created":"2021-02-20","cited_by_count":22,"area":null},{"id":"2102.13202","title":"Online Multi-Armed Bandits with Adaptive Inference","created":"2021-02-25","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":"2201.11341","title":"Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise","created":"2022-01-27","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":"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":"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":"2302.02252","title":"Reinforcement Learning in Low-Rank MDPs with Density Features","created":"2023-02-04","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":"2202.06915","title":"Stochastic linear optimization never overfits with quadratically-bounded losses on general data","created":"2022-02-14","cited_by_count":17,"area":null},{"id":"2205.14775","title":"An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledge","created":"2022-05-29","cited_by_count":17,"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":"2205.15294","title":"Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent","created":"2022-05-30","cited_by_count":15,"area":null},{"id":"2303.01049","title":"Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing","created":"2023-03-02","cited_by_count":15,"area":null},{"id":"2305.15877","title":"Exponential Smoothing for Off-Policy Learning","created":"2023-05-25","cited_by_count":15,"area":null},{"id":"2306.07923","title":"Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits","created":"2023-06-13","cited_by_count":15,"area":"offlinerl"},{"id":"2309.15771","title":"Importance-Weighted Offline Learning Done Right","created":"2023-09-27","cited_by_count":15,"area":"offlinerl"},{"id":"2102.07567","title":"Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent","created":"2021-02-15","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":"2208.02789","title":"Feature selection with gradient descent on two-layer networks in low-rotation regimes","created":"2022-08-04","cited_by_count":14,"area":null},{"id":"2302.01523","title":"Multi-channel Autobidding with Budget and ROI Constraints","created":"2023-02-03","cited_by_count":14,"area":null},{"id":"2210.08367","title":"Active Learning with Neural Networks: Insights from Nonparametric Statistics","created":"2022-10-15","cited_by_count":13,"area":null},{"id":"2205.15701","title":"Provable General Function Class Representation Learning in Multitask Bandits and MDPs","created":"2022-05-31","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":"2212.12180","title":"Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservices","created":"2022-12-23","cited_by_count":12,"area":null},{"id":"2102.09305","title":"Boosting for Online Convex Optimization","created":"2021-02-18","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":"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":"2307.05341","title":"Tracking Most Significant Shifts in Nonparametric Contextual Bandits","created":"2023-07-11","cited_by_count":10,"area":null},{"id":"2403.13578","title":"Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation","created":"2024-03-20","cited_by_count":10,"area":"alignment"},{"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":"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":"2107.11533","title":"Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Support","created":"2021-07-24","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":"2206.08364","title":"Interaction-Grounded Learning with Action-inclusive Feedback","created":"2022-06-16","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":"2211.12004","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":"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":"2303.01135","title":"Tight Risk Bounds for Gradient Descent on Separable Data","created":"2023-03-02","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":"2405.10027","title":"The Real Price of Bandit Information in Multiclass Classification","created":"2024-05-16","cited_by_count":7,"area":null},{"id":"2510.15464","title":"Learning to Answer from Correct Demonstrations","created":"2025-10-17","cited_by_count":7,"area":null},{"id":"2602.01381","title":"On the Power of (Approximate) Reward Models for Inference-Time Scaling","created":"2026-02-01","cited_by_count":7,"area":"lr"},{"id":"2106.07814","title":"Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2202.01721","title":"Variance-Optimal Augmentation Logging for Counterfactual Evaluation in Contextual Bandits","created":"2022-02-03","cited_by_count":6,"area":null},{"id":"2203.07338","title":"Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies","created":"2022-03-14","cited_by_count":6,"area":null},{"id":"2206.04907","title":"Efficient Heterogeneous Treatment Effect Estimation With Multiple Experiments and Multiple Outcomes","created":"2022-06-10","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":"2404.12648","title":"Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation","created":"2024-04-19","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":"2406.12406","title":"Fast Rates for Bandit PAC Multiclass Classification","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2411.00610","title":"Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation","created":"2024-11-01","cited_by_count":6,"area":"offlinerl"},{"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":"2209.12868","title":"On Efficient Online Imitation Learning via Classification","created":"2022-09-26","cited_by_count":5,"area":"offlinerl"},{"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":"2302.05430","title":"Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making","created":"2023-02-10","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":"2402.02700","title":"Sample Complexity Characterization for Linear Contextual MDPs","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2402.02701","title":"Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2402.10289","title":"Thompson Sampling in Partially Observable Contextual Bandits","created":"2024-02-15","cited_by_count":5,"area":null}],"next_cursor":"100"}