{"total":64,"rows":[{"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":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"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":"2106.03365","title":"Generalized Linear Bandits with Local Differential Privacy","created":"2021-06-07","cited_by_count":29,"area":null},{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29,"area":null},{"id":"2206.04405","title":"Conformal Off-Policy Prediction in Contextual Bandits","created":"2022-06-09","cited_by_count":25,"area":null},{"id":"2102.13202","title":"Online Multi-Armed Bandits with Adaptive Inference","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2106.00808","title":"Invariant Policy Learning: A Causal Perspective","created":"2021-06-01","cited_by_count":17,"area":null},{"id":"2306.07923","title":"Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits","created":"2023-06-13","cited_by_count":15,"area":"offlinerl"},{"id":"2102.05242","title":"Patterns, predictions, and actions: A story about machine learning","created":"2021-02-10","cited_by_count":14,"area":null},{"id":"2102.07567","title":"Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent","created":"2021-02-15","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":"2203.10079","title":"Simulating Bandit Learning from User Feedback for Extractive Question Answering","created":"2022-03-18","cited_by_count":14,"area":null},{"id":"2210.11834","title":"Optimal Contextual Bandits with Knapsacks under Realizability via Regression Oracles","created":"2022-10-21","cited_by_count":12,"area":null},{"id":"2212.12180","title":"Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservices","created":"2022-12-23","cited_by_count":12,"area":null},{"id":"2305.12473","title":"Continually Improving Extractive QA via Human Feedback","created":"2023-05-21","cited_by_count":11,"area":null},{"id":"2202.01914","title":"Tsetlin Machine for Solving Contextual Bandit Problems","created":"2022-02-04","cited_by_count":10,"area":null},{"id":"2306.06250","title":"Strategic Apple Tasting","created":"2023-06-09","cited_by_count":10,"area":null},{"id":"2403.13578","title":"Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation","created":"2024-03-20","cited_by_count":10,"area":"alignment"},{"id":"2211.15823","title":"Personalized Reward Learning with Interaction-Grounded Learning (IGL)","created":"2022-11-28","cited_by_count":9,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","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":"2101.01086","title":"Be Greedy in Multi-Armed Bandits","created":"2021-01-04","cited_by_count":7,"area":null},{"id":"2211.12004","title":"Contextual Bandits in a Survey Experiment on Charitable Giving: Within-Experiment Outcomes versus Policy Learning","created":"2022-11-22","cited_by_count":7,"area":null},{"id":"2202.01721","title":"Variance-Optimal Augmentation Logging for Counterfactual Evaluation in Contextual Bandits","created":"2022-02-03","cited_by_count":6,"area":null},{"id":"2405.06575","title":"No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization","created":"2024-05-10","cited_by_count":6,"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":"2402.10289","title":"Thompson Sampling in Partially Observable Contextual Bandits","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2105.10590","title":"Parallelizing Contextual Bandits","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2507.15290","title":"Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown","created":"2025-07-21","cited_by_count":4,"area":null},{"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":"2102.07387","title":"Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization","created":"2021-02-15","cited_by_count":3,"area":null},{"id":"2211.06569","title":"RISE: Robust Individualized Decision Learning with Sensitive Variables","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2302.01543","title":"Multiplier Bootstrap-based Exploration","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2306.14872","title":"Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits","created":"2023-06-26","cited_by_count":3,"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":"2410.08537","title":"Robust Offline Policy Learning with Observational Data from Multiple Sources","created":"2024-10-11","cited_by_count":3,"area":"offlinerl"},{"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":"2503.04010","title":"Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure","created":"2025-03-06","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":"2104.05613","title":"An Efficient Algorithm for Deep Stochastic Contextual Bandits","created":"2021-04-12","cited_by_count":1,"area":null},{"id":"2203.16668","title":"Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oracles","created":"2022-03-30","cited_by_count":1,"area":"alignment"},{"id":"2210.06302","title":"Maximum entropy exploration in contextual bandits with neural networks and energy based models","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2407.10115","title":"A Bag of Tricks for Scaling CPU-based Deep FFMs to more than 300m Predictions per Second","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2509.21613","title":"Multi-Objective Reinforcement Learning for Large Language Model Optimization: Visionary Perspective","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2605.27073","title":"Learning to Orchestrate Agents under Uncertainty","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.28433","title":"Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy","created":"2026-06-26","cited_by_count":1,"area":"deeprl"},{"id":"2609.07785","title":"What Does an LLM-Agent Leaderboard Rank Actually Compare?","created":"2026-09-07","cited_by_count":1,"area":"agents"},{"id":"2210.14077","title":"Eigen Memory Trees","created":"2022-10-25","cited_by_count":0,"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":"2305.12407","title":"Federated Offline Policy Learning","created":"2023-05-21","cited_by_count":0,"area":"offlinerl"},{"id":"2306.17329","title":"Kernel $\\epsilon$-Greedy for Multi-Armed Bandits with Covariates","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2408.04531","title":"AExGym: Benchmarks and Environments for Adaptive Experimentation","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2410.13109","title":"Latency-Aware Contextual Bandit: Application to Cryo-EM Data Collection","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2501.05309","title":"Private Selection with Heterogeneous Sensitivities","created":"2025-01-09","cited_by_count":0,"area":null},{"id":"2509.18447","title":"PrioriTouch: Adapting to User Contact Preferences for Whole-Arm Physical Human-Robot Interaction","created":"2025-09-22","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":"2602.05019","title":"A Simple Reduction Scheme for Constrained Contextual Bandits with Adversarial Contexts via Regression","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.11276","title":"RIE-Greedy: Regularization-Induced Exploration for Contextual Bandits","created":"2026-03-11","cited_by_count":0,"area":"alignment"},{"id":"2603.16755","title":"A Practical Algorithm for Feature-Rich, Non-Stationary Bandit Problems","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.01961","title":"Multi-User Dueling Bandits: A Fair Approach using Nash Social Welfare","created":"2026-05-03","cited_by_count":0,"area":"alignment"},{"id":"2609.06772","title":"CAROL: Context-Aware Online Learning for Fuzzer Scheduling","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.30273","title":"Offline Policy Evaluation as a decision support tool for designing Adaptive Experiments","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}