{"total":78,"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":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124,"area":null},{"id":"2102.07035","title":"Model-free Representation Learning and Exploration in Low-rank MDPs","created":"2021-02-14","cited_by_count":82,"area":null},{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"area":null},{"id":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81,"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":"2202.00063","title":"Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach","created":"2022-01-31","cited_by_count":51,"area":null},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49,"area":null},{"id":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48,"area":null},{"id":"2310.14554","title":"Making RL with Preference-based Feedback Efficient via Randomization","created":"2023-10-23","cited_by_count":46,"area":"alignment"},{"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":"2107.01264","title":"Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning","created":"2021-07-02","cited_by_count":34,"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":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","cited_by_count":31,"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":"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":"2104.06970","title":"Understanding the Eluder Dimension","created":"2021-04-14","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":"2205.10671","title":"Pessimism for Offline Linear Contextual Bandits using $\\ell_p$ Confidence Sets","created":"2022-05-21","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":"2207.02357","title":"Instance-optimal PAC Algorithms for Contextual Bandits","created":"2022-07-05","cited_by_count":16,"area":null},{"id":"2202.05448","title":"Fast Rates in Pool-Based Batch Active Learning","created":"2022-02-11","cited_by_count":15,"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":"2402.14987","title":"On the Performance of Empirical Risk Minimization with Smoothed Data","created":"2024-02-22","cited_by_count":13,"area":null},{"id":"2102.03400","title":"Confidence-Budget Matching for Sequential Budgeted Learning","created":"2021-02-05","cited_by_count":12,"area":null},{"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":"2307.04998","title":"Selective Sampling and Imitation Learning via Online Regression","created":"2023-07-11","cited_by_count":12,"area":"offlinerl"},{"id":"2310.06793","title":"Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning","created":"2023-10-10","cited_by_count":10,"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":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","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":"2107.02377","title":"A Short Note on the Relationship of Information Gain and Eluder Dimension","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2206.02326","title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","created":"2022-06-06","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":"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":"2302.07477","title":"Optimal Sample Complexity of Stable Discounted Markov Decision Processes","created":"2023-02-15","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":"2406.15753","title":"The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret","created":"2024-06-22","cited_by_count":6,"area":"alignment"},{"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":"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":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"},{"id":"2302.11634","title":"Provably Efficient Reinforcement Learning via Surprise Bound","created":"2023-02-22","cited_by_count":4,"area":null},{"id":"2401.12216","title":"Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning","created":"2024-01-22","cited_by_count":4,"area":"deeprl"},{"id":"2406.07455","title":"Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"id":"2407.01566","title":"A Parametric Contextual Online Learning Theory of Brokerage","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2506.06073","title":"System-Aware Unlearning Algorithms: Use Lesser, Forget Faster","created":"2025-06-06","cited_by_count":4,"area":"safety"},{"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":"2303.16998","title":"Does Sparsity Help in Learning Misspecified Linear Bandits?","created":"2023-03-29","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":"2609.33760","title":"Oracle-Efficient Online Classification with Stochastic Inputs and Adversarial Outputs","created":"2026-09-27","cited_by_count":3,"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":"2304.03321","title":"Adaptive Decision-Making with Constraints and Dependent Losses: Performance Guarantees and Applications to Online and Nonlinear Identification","created":"2023-04-06","cited_by_count":2,"area":null},{"id":"2403.04033","title":"Online Learning with Unknown Constraints","created":"2024-03-06","cited_by_count":2,"area":null},{"id":"2510.01620","title":"Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2510.08882","title":"An Improved Model-Free Decision-Estimation Coefficient with Applications in Adversarial MDPs","created":"2025-10-10","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":"2106.07203","title":"Online Sub-Sampling for Reinforcement Learning with General Function Approximation","created":"2021-06-14","cited_by_count":1,"area":null},{"id":"2308.15107","title":"Stochastic Graph Bandit Learning with Side-Observations","created":"2023-08-29","cited_by_count":1,"area":null},{"id":"2312.16341","title":"Harnessing the Power of Federated Learning in Federated Contextual Bandits","created":"2023-12-26","cited_by_count":1,"area":null},{"id":"2410.23434","title":"Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation","created":"2024-10-30","cited_by_count":1,"area":"deeprl"},{"id":"2503.00345","title":"Towards Understanding the Benefit of Multitask Representation Learning in Decision Process","created":"2025-03-01","cited_by_count":1,"area":"deeprl"},{"id":"2509.17092","title":"On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmark","created":"2025-09-21","cited_by_count":1,"area":"deeprl"},{"id":"2605.29645","title":"The Sample Complexity of Multiclass and Sparse Contextual Bandits","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2301.12571","title":"Bounded (O(1)) Regret Recommendation Learning via Synthetic Controls Oracle","created":"2023-01-29","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":"2506.00316","title":"Active Learning via Regression Beyond Realizability","created":"2025-05-31","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":"2511.01847","title":"Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2512.09513","title":"Contextual Dynamic Pricing with Heterogeneous Buyers","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2608.06559","title":"Bootstrap-Conditioned Action Selection with Tabular Foundation Models","created":"2026-08-06","cited_by_count":0,"area":"synth"}],"next_cursor":null}