{"total":57,"rows":[{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80,"area":null},{"id":"2202.00628","title":"Regret Minimization with Performative Feedback","created":"2022-02-01","cited_by_count":40,"area":null},{"id":"2102.05295","title":"An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2202.00150","title":"Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints","created":"2022-01-31","cited_by_count":29,"area":null},{"id":"2111.12151","title":"Best Arm Identification with Safety Constraints","created":"2021-11-23","cited_by_count":25,"area":null},{"id":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"area":null},{"id":"2402.15776","title":"Truly No-Regret Learning in Constrained MDPs","created":"2024-02-24","cited_by_count":23,"area":"deeprl"},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19,"area":null},{"id":"2206.11183","title":"Active Learning with Safety Constraints","created":"2022-06-22","cited_by_count":16,"area":null},{"id":"2202.13234","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","created":"2022-02-26","cited_by_count":15,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2206.05255","title":"Interactively Learning Preference Constraints in Linear Bandits","created":"2022-06-10","cited_by_count":11,"area":null},{"id":"2106.11692","title":"A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning","created":"2021-06-22","cited_by_count":9,"area":null},{"id":"2308.15006","title":"Directional Optimism for Safe Linear Bandits","created":"2023-08-29","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":"2203.15629","title":"Stochastic Conservative Contextual Linear Bandits","created":"2022-03-29","cited_by_count":6,"area":null},{"id":"2111.13415","title":"ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine","created":"2021-11-26","cited_by_count":5,"area":null},{"id":"2306.00172","title":"Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2306.06265","title":"Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2311.04338","title":"Convex Methods for Constrained Linear Bandits","created":"2023-11-07","cited_by_count":5,"area":null},{"id":"2111.04835","title":"Safe Data Collection for Offline and Online Policy Learning","created":"2021-11-08","cited_by_count":4,"area":null},{"id":"2111.12045","title":"Adaptive Multi-Goal Exploration","created":"2021-11-23","cited_by_count":4,"area":null},{"id":"2309.08709","title":"Price of Safety in Linear Best Arm Identification","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2104.08615","title":"Conservative Contextual Combinatorial Cascading Bandit","created":"2021-04-17","cited_by_count":3,"area":null},{"id":"2305.00889","title":"The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedback","created":"2023-05-01","cited_by_count":3,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2505.18407","title":"KL-regularization Itself is Differentially Private in Bandits and RLHF","created":"2025-05-23","cited_by_count":3,"area":"alignment"},{"id":"2102.12090","title":"Continuous Mean-Covariance Bandits","created":"2021-02-24","cited_by_count":2,"area":null},{"id":"2205.13689","title":"Safety Aware Changepoint Detection for Piecewise i.i.d. Bandits","created":"2022-05-27","cited_by_count":2,"area":null},{"id":"2207.14391","title":"Distributed Stochastic Bandit Learning with Delayed Context Observation","created":"2022-07-28","cited_by_count":2,"area":null},{"id":"2312.08559","title":"Fair Active Learning in Low-Data Regimes","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2401.11563","title":"Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraints","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2301.13393","title":"Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits","created":"2023-01-31","cited_by_count":1,"area":null},{"id":"2312.09961","title":"Risk-Aware Continuous Control with Neural Contextual Bandits","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2510.00602","title":"Multi-Agent Stage-wise Conservative Linear Bandits","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2604.16111","title":"Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2609.05820","title":"Online Learning with LLM Experts from Limited Feedback","created":"2026-09-05","cited_by_count":1,"area":null},{"id":"2302.03784","title":"Leveraging User-Triggered Supervision in Contextual Bandits","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2305.01202","title":"Exploration of Unranked Items in Safe Online Learning to Re-Rank","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2312.15458","title":"Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation","created":"2023-12-24","cited_by_count":0,"area":null},{"id":"2410.18844","title":"Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2510.01020","title":"The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.14884","title":"Learning When Not to Learn: Risk-Sensitive Abstention in Bandits with Unbounded Rewards","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2512.21165","title":"BALLAST: Bandit-Assisted Learning for Latency-Aware Stable Timeouts in Raft","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2601.12699","title":"Bandit Algorithms for Deep Brain Stimulation","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.07144","title":"BONSAI: Bayesian Optimization with Natural Simplicity and Interpretability","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2604.06451","title":"Quality-preserving Model for Electronics Production Quality Tests Reduction","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.20024","title":"Replicable Bandits with UCB based Exploration","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.01745","title":"NH-CROP: Robust Pricing for Governed Language Data Assets under Cost Uncertainty","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.09109","title":"When (and How) to Trust the Expert: Diagnosing Query-Time Expert-Guided Reinforcement Learning","created":"2026-05-09","cited_by_count":0,"area":"deeprl"},{"id":"2605.12176","title":"Multi-Task Representation Learning for Conservative Linear Bandits","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.04305","title":"Offline-to-Online Learning in Linear Bandits","created":"2026-06-03","cited_by_count":0,"area":"offlinerl"},{"id":"2606.20022","title":"Set Membership Estimation for Stochastic Linear Contextual Bandits","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.00215","title":"Personalizing Large Language Model Agents with Small Policy Models","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2609.34840","title":"Nociception as a Control Primitive: Afferent Channels and Nociceptive Memory for Agents Deployed in One Body","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39106","title":"Reserve-Aware Contrast Certificates for Conservative Bandits with Uncertain Baselines","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02932","title":"When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency","created":"2026-10-02","cited_by_count":0,"area":"agents"}],"next_cursor":null}