{"total":40,"rows":[{"id":"2111.05008","title":"Misspecified Gaussian Process Bandit Optimization","created":"2021-11-09","cited_by_count":55,"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":"2302.03673","title":"Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation","created":"2023-02-07","cited_by_count":27,"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":"2110.12615","title":"Linear Contextual Bandits with Adversarial Corruptions","created":"2021-10-25","cited_by_count":21,"area":null},{"id":"2301.12942","title":"Refined Regret for Adversarial MDPs with Linear Function Approximation","created":"2023-01-30","cited_by_count":19,"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":"2301.13087","title":"Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation","created":"2023-01-30","cited_by_count":17,"area":null},{"id":"2107.06327","title":"Contextual Games: Multi-Agent Learning with Side Information","created":"2021-07-13","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":"2402.11156","title":"Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits","created":"2024-02-17","cited_by_count":10,"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":"2102.05018","title":"Robust Bandit Learning with Imperfect Context","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2401.01857","title":"Optimal cross-learning for contextual bandits with unknown context distributions","created":"2024-01-03","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":"2306.07479","title":"Incentivizing High-Quality Content in Online Recommender Systems","created":"2023-06-13","cited_by_count":6,"area":null},{"id":"2310.01609","title":"Adversarial Contextual Bandits Go Kernelized","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2210.06719","title":"Reward Imputation with Sketching for Contextual Batched Bandits","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2406.00551","title":"Strategic Linear Contextual Bandits","created":"2024-06-01","cited_by_count":5,"area":null},{"id":"2207.08956","title":"Online Learning with Off-Policy Feedback","created":"2022-07-18","cited_by_count":4,"area":null},{"id":"2403.03219","title":"LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits","created":"2024-03-05","cited_by_count":4,"area":null},{"id":"2407.01566","title":"A Parametric Contextual Online Learning Theory of Brokerage","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2508.11931","title":"An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction","created":"2025-08-16","cited_by_count":4,"area":null},{"id":"2405.16581","title":"On Bits and Bandits: Quantifying the Regret-Information Trade-off","created":"2024-05-26","cited_by_count":3,"area":null},{"id":"2607.09015","title":"Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing","created":"2026-07-10","cited_by_count":3,"area":null},{"id":"2302.13252","title":"No-Regret Linear Bandits beyond Realizability","created":"2023-02-26","cited_by_count":2,"area":null},{"id":"2312.16489","title":"Best-of-Both-Worlds Linear Contextual Bandits","created":"2023-12-27","cited_by_count":2,"area":null},{"id":"2410.19705","title":"Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2508.18768","title":"Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits","created":"2025-08-26","cited_by_count":2,"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":"2606.14929","title":"Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2507.13639","title":"Differential Privacy in Kernelized Contextual Bandits via Random Projections","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2510.07424","title":"Best-of-Both Worlds for linear contextual bandits with paid observations","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2605.09200","title":"A Complete Characterization of Learnability for Adversarial Noisy Bandits","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.20022","title":"Set Membership Estimation for Stochastic Linear Contextual Bandits","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.31347","title":"Smart charging of large fleets of Electric Vehicles: Independent Multi-Agent Reinforcement Learning approaches","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.01080","title":"Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.09907","title":"Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2610.17818","title":"Follow the Perturbed Leader for Linear Bandits: $\\sqrt{T}$ Regret over General Convex Sets","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}