{"total":90,"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":"2310.03225","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","created":"2023-10-05","cited_by_count":28,"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":"2102.01229","title":"Doubly robust Thompson sampling for linear payoffs","created":"2021-02-01","cited_by_count":21,"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":"2201.10142","title":"Almost Optimal Variance-Constrained Best Arm Identification","created":"2022-01-25","cited_by_count":16,"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":"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":"2403.12948","title":"On Safety in Safe Bayesian Optimization","created":"2024-03-19","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":"2111.07430","title":"Safe Online Convex Optimization with Unknown Linear Safety Constraints","created":"2021-11-14","cited_by_count":13,"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":"2206.05255","title":"Interactively Learning Preference Constraints in Linear Bandits","created":"2022-06-10","cited_by_count":11,"area":null},{"id":"2207.10415","title":"Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning","created":"2022-07-21","cited_by_count":11,"area":null},{"id":"2111.04894","title":"Safe Policy Optimization with Local Generalized Linear Function Approximations","created":"2021-11-09","cited_by_count":10,"area":null},{"id":"2312.00561","title":"A safe exploration approach to constrained Markov decision processes","created":"2023-12-01","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":"2203.01198","title":"Linear Stochastic Bandits over a Bit-Constrained Channel","created":"2022-03-02","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":"2502.18655","title":"Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces","created":"2025-02-25","cited_by_count":7,"area":"deeprl"},{"id":"2203.15629","title":"Stochastic Conservative Contextual Linear Bandits","created":"2022-03-29","cited_by_count":6,"area":null},{"id":"2206.05404","title":"Squeeze All: Novel Estimator and Self-Normalized Bound for Linear Contextual Bandits","created":"2022-06-11","cited_by_count":6,"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":"2502.10138","title":"Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation","created":"2025-02-14","cited_by_count":6,"area":"deeprl"},{"id":"2110.13054","title":"Adaptive Data Debiasing through Bounded Exploration","created":"2021-10-25","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":"2209.08429","title":"Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems","created":"2022-09-17","cited_by_count":4,"area":null},{"id":"2302.12320","title":"Dynamic Regret Analysis of Safe Distributed Online Optimization for Convex and Non-convex Problems","created":"2023-02-23","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":"2405.05890","title":"Safe Exploration Using Bayesian World Models and Log-Barrier Optimization","created":"2024-05-09","cited_by_count":4,"area":"wm"},{"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":"2406.15648","title":"Testing the Feasibility of Linear Programs with Bandit Feedback","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2410.06474","title":"Flipping-based Policy for Chance-Constrained Markov Decision Processes","created":"2024-10-09","cited_by_count":3,"area":"deeprl"},{"id":"2501.00891","title":"Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts","created":"2025-01-01","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":"2111.14778","title":"Contextual Combinatorial Multi-output GP Bandits with Group Constraints","created":"2021-11-29","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":"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":"2405.15090","title":"Pure Exploration for Constrained Best Mixed Arm Identification with a Fixed Budget","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2505.20734","title":"Adversarial bandit optimization for approximately linear functions","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2506.08127","title":"Constrained Pareto Set Identification with Bandit Feedback","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2112.06728","title":"Safe Linear Leveling Bandits","created":"2021-12-13","cited_by_count":1,"area":null},{"id":"2211.01561","title":"Benefits of Monotonicity in Safe Exploration with Gaussian Processes","created":"2022-11-03","cited_by_count":1,"area":null},{"id":"2301.13393","title":"Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits","created":"2023-01-31","cited_by_count":1,"area":null},{"id":"2307.05698","title":"Online Ad Procurement in Non-stationary Autobidding Worlds","created":"2023-07-10","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":"2403.05786","title":"Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints","created":"2024-03-09","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":"2506.02386","title":"Asymptotically Optimal Linear Best Feasible Arm Identification with Fixed Budget","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2601.15552","title":"BanditLP: Large-Scale Stochastic Optimization for Personalized Recommendations","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2603.26066","title":"Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses","created":"2026-03-27","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":"2305.00254","title":"Semi-Infinitely Constrained Markov Decision Processes and Efficient Reinforcement Learning","created":"2023-04-29","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":"2308.10722","title":"Clustered Linear Contextual Bandits with Knapsacks","created":"2023-08-21","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":"2410.18844","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":"2509.12457","title":"On the Regularity and Fairness of Combinatorial Multi-Armed Bandit","created":"2025-09-15","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":"2602.05019","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":"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":"2605.12176","title":"Multi-Task Representation Learning for Conservative Linear Bandits","created":"2026-05-12","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":"2606.30932","title":"Personalizing Marketplace Policies with Competing Objectives and Constrained Experiments: Evidence from a Job Marketplace","created":"2026-06-29","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":"2607.16895","title":"When Can Safe Controllers Adapt? Information before Commitment","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.21993","title":"Gated Decoupled Compositional Bandits: A Unified Theory of Contextual Bandits with Supervised-Calibrated Action Scaling and Pre-Execution Gating","created":"2026-08-22","cited_by_count":0,"area":"alignment"},{"id":"2608.26755","title":"Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions","created":"2026-08-27","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}