{"total":127,"rows":[{"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":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"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":"2111.10919","title":"Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation","created":"2021-11-21","cited_by_count":71,"area":"offlinerl"},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2102.01748","title":"Near-Optimal Offline Reinforcement Learning via Double Variance Reduction","created":"2021-02-02","cited_by_count":56,"area":"offlinerl"},{"id":"2105.05806","title":"High-Dimensional Experimental Design and Kernel Bandits","created":"2021-05-12","cited_by_count":56,"area":null},{"id":"2111.05008","title":"Misspecified Gaussian Process Bandit Optimization","created":"2021-11-09","cited_by_count":55,"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":"2102.04132","title":"Near-optimal Representation Learning for Linear Bandits and Linear RL","created":"2021-02-08","cited_by_count":45,"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":"2107.01509","title":"Bayesian decision-making under misspecified priors with applications to meta-learning","created":"2021-07-03","cited_by_count":44,"area":null},{"id":"2102.11494","title":"Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games","created":"2021-02-23","cited_by_count":40,"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":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"area":null},{"id":"2105.13017","title":"Minimax Optimal Fixed-Budget Best Arm Identification in Linear Bandits","created":"2021-05-27","cited_by_count":32,"area":null},{"id":"2104.03781","title":"Leveraging Good Representations in Linear Contextual Bandits","created":"2021-04-08","cited_by_count":29,"area":null},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29,"area":null},{"id":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"area":null},{"id":"2105.08024","title":"Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting","created":"2021-05-17","cited_by_count":28,"area":null},{"id":"2210.12496","title":"Bayesian Optimization with Conformal Prediction Sets","created":"2022-10-22","cited_by_count":28,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2108.05533","title":"Efficient Local Planning with Linear Function Approximation","created":"2021-08-12","cited_by_count":23,"area":null},{"id":"2109.07340","title":"Distribution-free Contextual Dynamic Pricing","created":"2021-09-15","cited_by_count":22,"area":null},{"id":"2201.07052","title":"Differentially Private Reinforcement Learning with Linear Function Approximation","created":"2022-01-18","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":"2210.01898","title":"Replicable Bandits","created":"2022-10-04","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":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","cited_by_count":20,"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":"2102.02049","title":"On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function","created":"2021-02-03","cited_by_count":18,"area":null},{"id":"2107.09912","title":"Design of Experiments for Stochastic Contextual Linear Bandits","created":"2021-07-21","cited_by_count":18,"area":null},{"id":"2110.14798","title":"Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection","created":"2021-10-27","cited_by_count":18,"area":null},{"id":"2309.02236","title":"Distributionally Robust Model-based Reinforcement Learning with Large State Spaces","created":"2023-09-05","cited_by_count":17,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"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":"2302.12370","title":"Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds","created":"2023-02-24","cited_by_count":14,"area":null},{"id":"2106.12034","title":"Pure Exploration in Kernel and Neural Bandits","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2111.01479","title":"Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification","created":"2021-11-02","cited_by_count":12,"area":null},{"id":"2210.02087","title":"Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning","created":"2022-10-05","cited_by_count":12,"area":null},{"id":"2310.02717","title":"Online Clustering of Bandits with Misspecified User Models","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2202.01850","title":"A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits","created":"2022-02-03","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":"2110.09008","title":"When Are Linear Stochastic Bandits Attackable?","created":"2021-10-18","cited_by_count":10,"area":null},{"id":"2103.02729","title":"Linear Bandit Algorithms with Sublinear Time Complexity","created":"2021-03-03","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":"2412.00661","title":"Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning","created":"2024-12-01","cited_by_count":9,"area":null},{"id":"2207.05827","title":"Differentially Private Linear Bandits with Partial Distributed Feedback","created":"2022-07-12","cited_by_count":8,"area":null},{"id":"2210.12057","title":"Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization","created":"2022-10-21","cited_by_count":8,"area":null},{"id":"2210.15755","title":"Confident Approximate Policy Iteration for Efficient Local Planning in $q^\\pi$-realizable MDPs","created":"2022-10-27","cited_by_count":8,"area":null},{"id":"2308.15006","title":"Directional Optimism for Safe Linear Bandits","created":"2023-08-29","cited_by_count":8,"area":null},{"id":"2105.01136","title":"Learning Good State and Action Representations via Tensor Decomposition","created":"2021-05-03","cited_by_count":7,"area":null},{"id":"2110.02195","title":"TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions","created":"2021-10-05","cited_by_count":7,"area":null},{"id":"2203.04236","title":"A Complete Characterization of Linear Estimators for Offline Policy Evaluation","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2212.09510","title":"Near-optimal Policy Identification in Active Reinforcement Learning","created":"2022-12-19","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":"2402.15411","title":"Optimistic Information Directed Sampling","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2410.07533","title":"Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification","created":"2024-10-10","cited_by_count":7,"area":null},{"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":"2109.05546","title":"Improved Algorithms for Misspecified Linear Markov Decision Processes","created":"2021-09-12","cited_by_count":6,"area":null},{"id":"2302.04376","title":"Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning","created":"2023-02-08","cited_by_count":6,"area":null},{"id":"2303.09390","title":"On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits","created":"2023-03-16","cited_by_count":6,"area":null},{"id":"2403.14156","title":"Policy Mirror Descent with Lookahead","created":"2024-03-21","cited_by_count":6,"area":"deeprl"},{"id":"2408.04526","title":"Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs","created":"2024-08-08","cited_by_count":6,"area":"offlinerl"},{"id":"2506.23908","title":"Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence","created":"2025-06-30","cited_by_count":6,"area":"lr"},{"id":"2112.14195","title":"Exponential Family Model-Based Reinforcement Learning via Score Matching","created":"2021-12-28","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":"2405.06363","title":"Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs","created":"2024-05-10","cited_by_count":5,"area":"deeprl"},{"id":"2406.18529","title":"Confident Natural Policy Gradient for Local Planning in $q_\\pi$-realizable Constrained MDPs","created":"2024-06-26","cited_by_count":5,"area":"deeprl"},{"id":"2506.11831","title":"Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2601.15353","title":"Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions","created":"2026-01-21","cited_by_count":5,"area":"deeprl"},{"id":"2105.10590","title":"Parallelizing Contextual Bandits","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2109.05131","title":"Near Instance Optimal Model Selection for Pure Exploration Linear Bandits","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2208.05633","title":"Best Policy Identification in Linear MDPs","created":"2022-08-11","cited_by_count":4,"area":null},{"id":"2302.09703","title":"Reinforcement Learning with Function Approximation: From Linear to Nonlinear","created":"2023-02-20","cited_by_count":4,"area":null},{"id":"2302.12940","title":"Exponential Hardness of Reinforcement Learning with Linear Function Approximation","created":"2023-02-25","cited_by_count":4,"area":null},{"id":"2305.13185","title":"Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2310.19794","title":"Robust Causal Bandits for Linear Models","created":"2023-10-30","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":"2502.06142","title":"Linear Bandits with Partially Observable Features","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2210.03528","title":"Tractable Optimality in Episodic Latent MABs","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2301.12061","title":"(Private) Kernelized Bandits with Distributed Biased Feedback","created":"2023-01-28","cited_by_count":3,"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":"2307.13332","title":"The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2404.10745","title":"Achieving Constant Regret in Linear Markov Decision Processes","created":"2024-04-16","cited_by_count":3,"area":"deeprl"},{"id":"2501.00891","title":"Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2106.09973","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2110.03424","title":"Bad-Policy Density: A Measure of Reinforcement Learning Hardness","created":"2021-10-07","cited_by_count":2,"area":null},{"id":"2111.08066","title":"Exploiting Action Impact Regularity and Exogenous State Variables for Offline Reinforcement Learning","created":"2021-11-15","cited_by_count":2,"area":"offlinerl"},{"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":"2302.13252","title":"No-Regret Linear Bandits beyond Realizability","created":"2023-02-26","cited_by_count":2,"area":null},{"id":"2310.01616","title":"Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity","created":"2023-10-02","cited_by_count":2,"area":"offlinerl"},{"id":"2310.07811","title":"Online RL in Linearly $q^\\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore","created":"2023-10-11","cited_by_count":2,"area":null},{"id":"2405.07795","title":"Improved Bound for Robust Causal Bandits with Linear Models","created":"2024-05-13","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":"2407.13887","title":"Learning Goal-Conditioned Representations for Language Reward Models","created":"2024-07-18","cited_by_count":2,"area":"alignment"}],"next_cursor":"100"}