{"total":71,"rows":[{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"area":null},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62,"area":null},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55,"area":null},{"id":"2111.05008","title":"Misspecified Gaussian Process Bandit Optimization","created":"2021-11-09","cited_by_count":55,"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":"2104.03781","title":"Leveraging Good Representations in Linear Contextual Bandits","created":"2021-04-08","cited_by_count":29,"area":null},{"id":"2210.01078","title":"Unsupervised Model Selection for Time-series Anomaly Detection","created":"2022-10-03","cited_by_count":25,"area":null},{"id":"2110.13282","title":"The Pareto Frontier of model selection for general Contextual Bandits","created":"2021-10-25","cited_by_count":24,"area":null},{"id":"2106.03243","title":"Neural Active Learning with Performance Guarantees","created":"2021-06-06","cited_by_count":22,"area":null},{"id":"2109.07340","title":"Distribution-free Contextual Dynamic Pricing","created":"2021-09-15","cited_by_count":22,"area":null},{"id":"2202.06151","title":"Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits","created":"2022-02-12","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":"2110.12615","title":"Linear Contextual Bandits with Adversarial Corruptions","created":"2021-10-25","cited_by_count":21,"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":"2212.03798","title":"Stochastic Rising Bandits","created":"2022-12-07","cited_by_count":18,"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":"2305.18543","title":"Robust Lipschitz Bandits to Adversarial Corruptions","created":"2023-05-29","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":"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":"2211.02016","title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning","created":"2022-11-03","cited_by_count":13,"area":"offlinerl"},{"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":"2111.01479","title":"Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification","created":"2021-11-02","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":"2112.12320","title":"Model Selection in Batch Policy Optimization","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2206.14912","title":"Best of Both Worlds Model Selection","created":"2022-06-29","cited_by_count":11,"area":null},{"id":"2306.02869","title":"Data-Driven Online Model Selection With Regret Guarantees","created":"2023-06-05","cited_by_count":11,"area":null},{"id":"2306.10259","title":"Active Policy Improvement from Multiple Black-box Oracles","created":"2023-06-17","cited_by_count":11,"area":"offlinerl"},{"id":"2312.15433","title":"Best-of-Both-Worlds Algorithms for Linear Contextual Bandits","created":"2023-12-24","cited_by_count":11,"area":null},{"id":"2404.12522","title":"Neural Active Learning Beyond Bandits","created":"2024-04-18","cited_by_count":10,"area":null},{"id":"2107.03455","title":"Model Selection for Generic Contextual Bandits","created":"2021-07-07","cited_by_count":8,"area":null},{"id":"2203.04274","title":"Leveraging Initial Hints for Free in Stochastic Linear Bandits","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2302.02944","title":"Learning Complementary Policies for Human-AI Teams","created":"2023-02-06","cited_by_count":7,"area":null},{"id":"2501.02926","title":"Offline-to-online hyperparameter transfer for stochastic bandits","created":"2025-01-06","cited_by_count":7,"area":"offlinerl"},{"id":"2109.05546","title":"Improved Algorithms for Misspecified Linear Markov Decision Processes","created":"2021-09-12","cited_by_count":6,"area":null},{"id":"2207.12805","title":"Neural Design for Genetic Perturbation Experiments","created":"2022-07-26","cited_by_count":6,"area":null},{"id":"2302.08345","title":"Linear Bandits with Memory: from Rotting to Rising","created":"2023-02-16","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":"2404.09494","title":"On the Necessity of Collaboration for Online Model Selection with Decentralized Data","created":"2024-04-15","cited_by_count":6,"area":null},{"id":"2410.13837","title":"ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization","created":"2024-10-17","cited_by_count":6,"area":"deeprl"},{"id":"2106.05378","title":"Feature and Parameter Selection in Stochastic Linear Bandits","created":"2021-06-09","cited_by_count":5,"area":null},{"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":"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":"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":"2109.05131","title":"Near Instance Optimal Model Selection for Pure Exploration Linear Bandits","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2210.15513","title":"Lifelong Bandit Optimization: No Prior and No Regret","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2112.02185","title":"Neural Pseudo-Label Optimism for the Bank Loan Problem","created":"2021-12-03","cited_by_count":3,"area":null},{"id":"2402.07588","title":"Understanding Model Selection For Learning In Strategic Environments","created":"2024-02-12","cited_by_count":3,"area":null},{"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":"2406.01192","title":"Sparsity-Agnostic Linear Bandits with Adaptive Adversaries","created":"2024-06-03","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":"2602.00966","title":"Symphony-Coord: Adaptive Routing for Multi-Agent LLM Systems","created":"2026-02-01","cited_by_count":2,"area":"agents"},{"id":"2107.05849","title":"Model Selection for Generic Reinforcement Learning","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2205.14839","title":"Adversarial Bandits against Arbitrary Strategies","created":"2022-05-30","cited_by_count":1,"area":null},{"id":"2207.02992","title":"Model Selection in Reinforcement Learning with General Function Approximations","created":"2022-07-06","cited_by_count":1,"area":null},{"id":"2401.10478","title":"Budgeted Online Model Selection and Fine-Tuning via Federated Learning","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2406.04081","title":"Bootstrapping Expectiles in Reinforcement Learning","created":"2024-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2408.08859","title":"Stochastic Bandits Robust to Adversarial Attacks","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2510.22654","title":"Managing Self-Learning Experts under Per-Round Budget Constraints","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2602.07418","title":"Achieving Optimal Static and Dynamic Regret Simultaneously in Bandits with Deterministic Losses","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2302.09451","title":"Estimating Optimal Policy Value in General Linear Contextual Bandits","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2402.17720","title":"The SMART approach to instance-optimal online learning","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2408.04046","title":"Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives","created":"2024-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2409.18439","title":"State-free Reinforcement Learning","created":"2024-09-27","cited_by_count":0,"area":"deeprl"},{"id":"2512.02214","title":"Improved Training Mechanism for Reinforcement Learning via Online Model Selection","created":"2025-12-01","cited_by_count":0,"area":"deeprl"},{"id":"2602.17958","title":"Bayesian Online Model Selection","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2605.08558","title":"Beyond Static Bias: Adaptive Multi-Fidelity Bandits with Improving Proxies","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.27917","title":"Graph Dimensionality Reduction for Contextual Bandits: Structure-Specific Regret Bounds under Approximate Smoothness and Noisy Eigenspaces","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2609.06514","title":"Model-Adaptive and Risk-Constrained Frequency Hopping Against Predictive Jammers","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":null}