{"total":21,"rows":[{"id":"2111.06537","title":"Multi-Step Budgeted Bayesian Optimization with Unknown Evaluation Costs","created":"2021-11-12","cited_by_count":18,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2101.01086","title":"Be Greedy in Multi-Armed Bandits","created":"2021-01-04","cited_by_count":7,"area":null},{"id":"2103.12198","title":"Challenges in Statistical Analysis of Data Collected by a Bandit Algorithm: An Empirical Exploration in Applications to Adaptively Randomized Experiments","created":"2021-03-22","cited_by_count":6,"area":null},{"id":"2304.05219","title":"BanditQ: Fair Bandits with Guaranteed Rewards","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2306.07071","title":"Budgeted Multi-Armed Bandits with Asymmetric Confidence Intervals","created":"2023-06-12","cited_by_count":6,"area":null},{"id":"2106.05165","title":"A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2608.04333","title":"Cost-Aware Multi-Objective Bandits: Theory and Application to Budgeted LLM Configuration Evaluation","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2105.08869","title":"Incentivized Bandit Learning with Self-Reinforcing User Preferences","created":"2021-05-19","cited_by_count":2,"area":null},{"id":"2106.01135","title":"MNL-Bandit with Knapsacks: a near-optimal algorithm","created":"2021-06-02","cited_by_count":2,"area":null},{"id":"2107.05992","title":"Identifying Influential Users in Unknown Social Networks for Adaptive Incentive Allocation Under Budget Restriction","created":"2021-07-13","cited_by_count":2,"area":null},{"id":"2203.09578","title":"GAC: A Deep Reinforcement Learning Model Toward User Incentivization in Unknown Social Networks","created":"2022-03-17","cited_by_count":2,"area":null},{"id":"2408.15535","title":"Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2211.08311","title":"On Penalization in Stochastic Multi-armed Bandits","created":"2022-11-15","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":"2305.08664","title":"MADDM: Multi-Advisor Dynamic Binary Decision-Making by Maximizing the Utility","created":"2023-05-15","cited_by_count":0,"area":null},{"id":"2305.09626","title":"Balancing Risk and Reward: An Automated Phased Release Strategy","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2408.04531","title":"AExGym: Benchmarks and Environments for Adaptive Experimentation","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2508.13657","title":"In-Context Decision Making for Optimizing Complex AutoML Pipelines","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2604.26169","title":"Budget-Constrained Causal Bandits: Bridging Uplift Modeling and Sequential Decision-Making","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2608.01341","title":"402Pilot: An x402 Decision Layer for Autonomous Agent Micropayments","created":"2026-08-02","cited_by_count":0,"area":null}],"next_cursor":null}