{"total":66,"rows":[{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247,"area":null},{"id":"2206.11889","title":"Provably Efficient Model-Free Constrained RL with Linear Function Approximation","created":"2022-06-23","cited_by_count":31,"area":null},{"id":"2101.08534","title":"Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback","created":"2021-01-21","cited_by_count":21,"area":null},{"id":"2110.00202","title":"Batched Thompson Sampling","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2301.13326","title":"A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback","created":"2023-01-30","cited_by_count":19,"area":null},{"id":"2302.01324","title":"Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback","created":"2023-02-02","cited_by_count":19,"area":null},{"id":"2201.11921","title":"Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits","created":"2022-01-28","cited_by_count":18,"area":null},{"id":"2312.08057","title":"Combinatorial Stochastic-Greedy Bandit","created":"2023-12-13","cited_by_count":18,"area":null},{"id":"2306.00242","title":"Combinatorial Neural Bandits","created":"2023-05-31","cited_by_count":16,"area":null},{"id":"2401.02749","title":"Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding","created":"2024-01-05","cited_by_count":15,"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":"2206.06810","title":"Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds","created":"2022-06-14","cited_by_count":12,"area":null},{"id":"2405.05950","title":"Federated Combinatorial Multi-Agent Multi-Armed Bandits","created":"2024-05-09","cited_by_count":11,"area":null},{"id":"2206.09341","title":"Bayesian Optimization under Stochastic Delayed Feedback","created":"2022-06-19","cited_by_count":10,"area":null},{"id":"2102.00725","title":"Generalized non-stationary bandits","created":"2021-02-01","cited_by_count":8,"area":null},{"id":"2105.10721","title":"From Finite to Countable-Armed Bandits","created":"2021-05-22","cited_by_count":8,"area":null},{"id":"2106.13669","title":"Multi-player Multi-armed Bandits with Collision-Dependent Reward Distributions","created":"2021-06-25","cited_by_count":8,"area":null},{"id":"2205.11168","title":"Logarithmic regret bounds for continuous-time average-reward Markov decision processes","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2309.16044","title":"Improving Adaptive Online Learning Using Refined Discretization","created":"2023-09-27","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":"2404.17709","title":"Low-rank Matrix Bandits with Heavy-tailed Rewards","created":"2024-04-26","cited_by_count":7,"area":null},{"id":"2211.10293","title":"Dueling Bandits: From Two-dueling to Multi-dueling","created":"2022-11-16","cited_by_count":4,"area":null},{"id":"2403.00116","title":"Federated Linear Contextual Bandits with Heterogeneous Clients","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2202.13448","title":"Federated Online Sparse Decision Making","created":"2022-02-27","cited_by_count":3,"area":null},{"id":"2304.06104","title":"Primal-Dual Contextual Bayesian Optimization for Control System Online Optimization with Time-Average Constraints","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2101.01572","title":"Sequential Choice Bandits with Feedback for Personalizing users' experience","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2201.00486","title":"Using Non-Stationary Bandits for Learning in Repeated Cournot Games with Non-Stationary Demand","created":"2022-01-03","cited_by_count":2,"area":null},{"id":"2201.01628","title":"Bridging Adversarial and Nonstationary Multi-armed Bandit","created":"2022-01-05","cited_by_count":2,"area":null},{"id":"2207.01393","title":"Autonomous Drug Design with Multi-Armed Bandits","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2207.05437","title":"Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model","created":"2022-07-12","cited_by_count":2,"area":null},{"id":"2510.10730","title":"Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2510.19471","title":"Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2604.21432","title":"A single algorithm for both restless and rested rotting bandits","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2106.07203","title":"Online Sub-Sampling for Reinforcement Learning with General Function Approximation","created":"2021-06-14","cited_by_count":1,"area":null},{"id":"2108.12547","title":"Dynamic Selection in Algorithmic Decision-making","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2110.12118","title":"Bandits with Dynamic Arm-acquisition Costs","created":"2021-10-23","cited_by_count":1,"area":null},{"id":"2210.10278","title":"A Reinforcement Learning Approach in Multi-Phase Second-Price Auction Design","created":"2022-10-19","cited_by_count":1,"area":null},{"id":"2306.05150","title":"Bayesian Optimization of Expensive Nested Grey-Box Functions","created":"2023-06-08","cited_by_count":1,"area":null},{"id":"2405.02188","title":"Optimistic Regret Bounds for Online Learning in Adversarial Markov Decision Processes","created":"2024-05-03","cited_by_count":1,"area":null},{"id":"2405.14038","title":"FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2412.19252","title":"Localized exploration in contextual dynamic pricing achieves dimension-free regret","created":"2024-12-26","cited_by_count":1,"area":null},{"id":"2501.01291","title":"Detection Augmented Bandit Procedures for Piecewise Stationary MABs: A Modular Approach","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2502.14043","title":"Safe Learning Under Irreversible Dynamics via Asking for Help","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2510.07646","title":"Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2510.22579","title":"Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2602.00417","title":"Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2606.14929","title":"Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2608.07139","title":"Online Conformal Prediction Beyond Feedback","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2102.05164","title":"Nonstochastic Bandits with Infinitely Many Experts","created":"2021-02-09","cited_by_count":0,"area":null},{"id":"2111.13026","title":"Bandit problems with fidelity rewards","created":"2021-11-25","cited_by_count":0,"area":null},{"id":"2301.00561","title":"Local Differential Privacy for Sequential Decision Making in a Changing Environment","created":"2023-01-02","cited_by_count":0,"area":null},{"id":"2304.00999","title":"Bandits for Sponsored Search Auctions under Unknown Valuation Model: Case Study in E-Commerce Advertising","created":"2023-03-31","cited_by_count":0,"area":null},{"id":"2305.19691","title":"Constant or logarithmic regret in asynchronous multiplayer bandits","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2306.15856","title":"Pure exploration in multi-armed bandits with low rank structure using oblivious sampler","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2310.00962","title":"Multi-Agent Bayesian Optimization with Coupled Black-Box and Affine Constraints","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2502.15240","title":"Multi-agent Multi-armed Bandits with Minimum Reward Guarantee Fairness","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2512.21794","title":"Multi-agent Adaptive Mechanism Design","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2602.02087","title":"Efficient Swap Regret Minimization in Combinatorial Bandits","created":"2026-02-02","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":"2605.19584","title":"Online Market Making and the Value of Observing the Order Book","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.23351","title":"Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2607.01080","title":"Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.08268","title":"Learning under Opponent Unawareness in Linear-Quadratic Stochastic Games","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.12134","title":"Adversarial Resilience of Poisson-Process Submodular Maximization over Matroids, and Full-Bandit Learning","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.13954","title":"Linear Ensemble Sampling with Smaller Ensembles","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2610.14904","title":"Prediction with Expert Advice under Heavy-Tailed Losses","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}