{"total":63,"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":"2106.06239","title":"Safe Reinforcement Learning with Linear Function Approximation","created":"2021-06-11","cited_by_count":35,"area":null},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35,"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":"2302.04375","title":"A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints","created":"2023-02-08","cited_by_count":17,"area":null},{"id":"2206.11183","title":"Active Learning with Safety Constraints","created":"2022-06-22","cited_by_count":16,"area":null},{"id":"2109.10458","title":"Achieving Counterfactual Fairness for Causal Bandit","created":"2021-09-21","cited_by_count":15,"area":null},{"id":"2204.00706","title":"Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk","created":"2022-04-01","cited_by_count":15,"area":null},{"id":"2209.13694","title":"Safe Linear Bandits over Unknown Polytopes","created":"2022-09-27","cited_by_count":14,"area":null},{"id":"2102.10156","title":"Learning to Persuade on the Fly: Robustness Against Ignorance","created":"2021-02-19","cited_by_count":12,"area":null},{"id":"2206.07316","title":"Online Contextual Decision-Making with a Smart Predict-then-Optimize Method","created":"2022-06-15","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":"2306.12774","title":"Pure Exploration in Bandits with Linear Constraints","created":"2023-06-22","cited_by_count":10,"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":"2211.14768","title":"Constrained Pure Exploration Multi-Armed Bandits with a Fixed Budget","created":"2022-11-27","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":"2312.14470","title":"Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration","created":"2023-12-22","cited_by_count":7,"area":null},{"id":"2407.01795","title":"Honor Among Bandits: No-Regret Learning for Online Fair Division","created":"2024-07-01","cited_by_count":7,"area":null},{"id":"2301.11547","title":"Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation","created":"2023-01-27","cited_by_count":6,"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":"2506.13244","title":"No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!","created":"2025-06-16","cited_by_count":5,"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":"2305.18511","title":"Contextual Bandits with Budgeted Information Reveal","created":"2023-05-29","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":"2406.15648","title":"Testing the Feasibility of Linear Programs with Bandit Feedback","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2501.07022","title":"Improved Regret Bounds for Online Fair Division with Bandit Learning","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2105.08748","title":"Learning to Act Safely with Limited Exposure and Almost Sure Certainty","created":"2021-05-18","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":"2301.13791","title":"Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback","created":"2023-01-31","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":"2403.04033","title":"Online Learning with Unknown Constraints","created":"2024-03-06","cited_by_count":2,"area":null},{"id":"2410.17382","title":"Cooperative Multi-Agent Constrained Stochastic Linear Bandits","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2505.20010","title":"Data-Dependent Regret Bounds for Constrained MABs","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2602.14580","title":"Replicable Constrained Bandits","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2605.14553","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2403.05786","title":"Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2404.09123","title":"Provable Interactive Learning with Hindsight Instruction Feedback","created":"2024-04-14","cited_by_count":1,"area":null},{"id":"2505.07101","title":"Constrained Online Decision-Making: A Unified Framework","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2506.03062","title":"Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation","created":"2025-06-03","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":"2305.14537","title":"Disincentivizing Polarization in Social Networks","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2311.04731","title":"Robust Best-arm Identification in Linear Bandits","created":"2023-11-08","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":"2410.03651","title":"Minimax-optimal trust-aware multi-armed bandits","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2410.13108","title":"Algorithmic Content Selection and the Impact of User Disengagement","created":"2024-10-17","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":"2412.03983","title":"Safe and Efficient Online Convex Optimization with Linear Budget Constraints and Partial Feedback","created":"2024-12-05","cited_by_count":0,"area":null},{"id":"2503.02043","title":"Constrained Linear Thompson Sampling","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2504.16371","title":"The Safety-Privacy Tradeoff in Linear Bandits","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2507.18975","title":"Secure Best Arm Identification in the Presence of a Copycat","created":"2025-07-25","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":"2510.07635","title":"Safely Exploring Novel Actions in Recommender Systems via Deployment-Efficient Policy Learning","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.12523","title":"Multi-Armed Bandits with Minimum Aggregated Revenue Constraints","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2602.14543","title":"Truly Adapting to Adversarial Constraints in Constrained MABs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2605.07304","title":"Latent Order Bandits","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.09802","title":"Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.05620","title":"Safe Bayesian Optimization with Counterfactual Policies","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.37902","title":"You Cannot Pick a Provider From the Price List: Market-Aware Routing for Open-Weight LLM Inference","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01377","title":"Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}