{"total":61,"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":"2110.07788","title":"Gaussian Process Bandit Optimization with Few Batches","created":"2021-10-15","cited_by_count":57,"area":null},{"id":"2101.00494","title":"A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost","created":"2021-01-02","cited_by_count":40,"area":null},{"id":"2102.03758","title":"Non-stationary Online Learning with Memory and Non-stochastic Control","created":"2021-02-07","cited_by_count":33,"area":null},{"id":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32,"area":null},{"id":"2102.06933","title":"Revisiting Smoothed Online Learning","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2102.13028","title":"Batched Neural Bandits","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2210.01898","title":"Replicable Bandits","created":"2022-10-04","cited_by_count":22,"area":null},{"id":"2110.09722","title":"Lipschitz Bandits with Batched Feedback","created":"2021-10-19","cited_by_count":21,"area":null},{"id":"2110.00202","title":"Batched Thompson Sampling","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2207.07974","title":"Online Prediction in Sub-linear Space","created":"2022-07-16","cited_by_count":16,"area":null},{"id":"2102.01623","title":"Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory","created":"2021-02-02","cited_by_count":14,"area":null},{"id":"2102.03803","title":"Lazy OCO: Online Convex Optimization on a Switching Budget","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2210.00701","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2210.08238","title":"Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning","created":"2022-10-15","cited_by_count":13,"area":"offlinerl"},{"id":"2105.09232","title":"Diffusion Approximations for Thompson Sampling in the Small Gap Regime","created":"2021-05-19","cited_by_count":12,"area":null},{"id":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11,"area":null},{"id":"2205.06846","title":"Optimal Comparator Adaptive Online Learning with Switching Cost","created":"2022-05-13","cited_by_count":9,"area":null},{"id":"2302.01539","title":"A Lipschitz Bandits Approach for Continuous Hyperparameter Optimization","created":"2023-02-03","cited_by_count":9,"area":null},{"id":"2209.11837","title":"Doubly Fair Dynamic Pricing","created":"2022-09-23","cited_by_count":8,"area":null},{"id":"2301.13397","title":"Sequential Strategic Screening","created":"2023-01-31","cited_by_count":8,"area":null},{"id":"2305.19036","title":"Delayed Bandits: When Do Intermediate Observations Help?","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2403.07413","title":"Learning-Augmented Algorithms with Explicit Predictors","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2302.01477","title":"A Reduction-based Framework for Sequential Decision Making with Delayed Feedback","created":"2023-02-03","cited_by_count":7,"area":null},{"id":"2102.10616","title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition","created":"2021-02-21","cited_by_count":5,"area":null},{"id":"2306.09588","title":"Understanding the Role of Feedback in Online Learning with Switching Costs","created":"2023-06-16","cited_by_count":4,"area":null},{"id":"2402.01111","title":"Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints","created":"2024-02-02","cited_by_count":4,"area":"deeprl"},{"id":"2202.06657","title":"The Impact of Batch Learning in Stochastic Linear Bandits","created":"2022-02-14","cited_by_count":3,"area":null},{"id":"2204.11174","title":"Complete Policy Regret Bounds for Tallying Bandits","created":"2022-04-24","cited_by_count":3,"area":null},{"id":"2303.01709","title":"Streaming Algorithms for Learning with Experts: Deterministic Versus Robust","created":"2023-03-03","cited_by_count":3,"area":null},{"id":"2310.02261","title":"Adaptive Online Non-stochastic Control","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2402.17732","title":"Batched Nonparametric Contextual Bandits","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2603.12627","title":"Batched Kernelized Bandits: Refinements and Extensions","created":"2026-03-13","cited_by_count":3,"area":null},{"id":"2106.15662","title":"Exponential Weights Algorithms for Selective Learning","created":"2021-06-29","cited_by_count":2,"area":null},{"id":"2108.06812","title":"Batched Thompson Sampling for Multi-Armed Bandits","created":"2021-08-15","cited_by_count":2,"area":null},{"id":"2205.15891","title":"One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning","created":"2022-05-31","cited_by_count":2,"area":null},{"id":"2305.02955","title":"Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2306.07163","title":"A Batch-to-Online Transformation under Random-Order Model","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2402.07391","title":"Replicability is Asymptotically Free in Multi-armed Bandits","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2405.05733","title":"Batched Stochastic Bandit for Nondegenerate Functions","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2506.05479","title":"Learning-Augmented Algorithms for MTS with Bandit Access to Multiple Predictors","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2510.02820","title":"Online Learning in the Random Order Model","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2601.15984","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2602.06902","title":"Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memory","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2111.02071","title":"The Impact of Batch Learning in Stochastic Bandits","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2603.13742","title":"Few Batches or Little Memory, But Not Both: Simultaneous Space and Adaptivity Constraints in Stochastic Bandits","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2605.30976","title":"Batched Stochastic Linear Bandits with 1-Bit Communication Constraints","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2107.05289","title":"Continuous Time Bandits With Sampling Costs","created":"2021-07-12","cited_by_count":0,"area":null},{"id":"2111.13026","title":"Bandit problems with fidelity rewards","created":"2021-11-25","cited_by_count":0,"area":null},{"id":"2112.06424","title":"A Benchmark for Low-Switching-Cost Reinforcement Learning","created":"2021-12-13","cited_by_count":0,"area":null},{"id":"2410.14533","title":"The Traveling Bandit: A Framework for Bayesian Optimization with Movement Costs","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2501.17370","title":"Breaking the $\\log(1/\\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids","created":"2025-01-29","cited_by_count":0,"area":null},{"id":"2504.03499","title":"Optimistic Learning for Communication Networks","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2510.03798","title":"Batched Bandits with Heavy-Tailed Rewards","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2511.03708","title":"The Adaptivity Barrier in Batched Nonparametric Bandits: Sharp Characterization of the Price of Unknown Margin","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2606.02363","title":"Minimax-Optimal Policy Regret in Partially Observable Markov Games","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.27448","title":"Learning in Markovian bandits with non-observable states and constrained decision epochs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.31449","title":"Contextual Slate GLM Bandits with Limited Adaptivity","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.09366","title":"Beyond Binary: Continuous State Optimization with Graph-Structured Objectives","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.30556","title":"Dynamic Regret in Online Convex Optimization with Indicator Switching Costs","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.14790","title":"Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}