{"total":59,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"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":"2310.16608","title":"Performative Prediction: Past and Future","created":"2023-10-25","cited_by_count":53,"area":null},{"id":"2202.00628","title":"Regret Minimization with Performative Feedback","created":"2022-02-01","cited_by_count":40,"area":null},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"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":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"area":null},{"id":"2104.14527","title":"Online certification of preference-based fairness for personalized recommender systems","created":"2021-04-29","cited_by_count":22,"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":"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":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"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":"2102.05018","title":"Robust Bandit Learning with Imperfect Context","created":"2021-02-09","cited_by_count":8,"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":"2102.05990","title":"Robust Generalization and Safe Query-Specialization in Counterfactual Learning to Rank","created":"2021-02-11","cited_by_count":6,"area":null},{"id":"2203.15629","title":"Stochastic Conservative Contextual Linear Bandits","created":"2022-03-29","cited_by_count":6,"area":null},{"id":"2502.08259","title":"Balancing optimism and pessimism in offline-to-online learning","created":"2025-02-12","cited_by_count":6,"area":"offlinerl"},{"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":"2111.04835","title":"Safe Data Collection for Offline and Online Policy Learning","created":"2021-11-08","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":"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":"2205.13689","title":"Safety Aware Changepoint Detection for Piecewise i.i.d. Bandits","created":"2022-05-27","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":"2502.11673","title":"Best of Both Worlds: Regret Minimization versus Minimax Play","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2109.03747","title":"Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values","created":"2021-09-08","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":"2306.10158","title":"Learning-Augmented Decentralized Online Convex Optimization in Networks","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2311.01568","title":"Anytime-Competitive Reinforcement Learning with Policy Prior","created":"2023-11-02","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":"2609.05820","title":"Online Learning with LLM Experts from Limited Feedback","created":"2026-09-05","cited_by_count":1,"area":null},{"id":"2103.03307","title":"Conservative Optimistic Policy Optimization via Multiple Importance Sampling","created":"2021-03-04","cited_by_count":0,"area":null},{"id":"2203.00822","title":"Keeping Minimal Experience to Achieve Efficient Interpretable Policy Distillation","created":"2022-03-02","cited_by_count":0,"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":"2305.14537","title":"Disincentivizing Polarization in Social Networks","created":"2023-05-23","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":"2312.15595","title":"Zero-Inflated Bandits","created":"2023-12-25","cited_by_count":0,"area":null},{"id":"2501.18560","title":"Bandits with Anytime Knapsacks","created":"2025-01-30","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":"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":"2603.22348","title":"Learning Safely Without Knowing the World:COMPASS-Hedge","created":"2026-03-22","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":"2605.07171","title":"Cost-Ordered Feasibility for Multi-Armed Bandits with Cost Subsidy","created":"2026-05-08","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":"2607.29400","title":"ALIVE: Warnings Before Exclusion in Budgeted Multi-Source Learning","created":"2026-07-31","cited_by_count":0,"area":null},{"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":"2609.37902","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":"2609.39106","title":"Reserve-Aware Contrast Certificates for Conservative Bandits with Uncertain Baselines","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03646","title":"When May a Bandit Leave Its Anchor? E-Process-Authorized Thompson Sampling under Non-stationarity","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}