{"total":71,"rows":[{"id":"2106.02436","title":"Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions","created":"2021-06-04","cited_by_count":34,"area":null},{"id":"2208.09407","title":"Learning in Stackelberg Games with Non-myopic Agents","created":"2022-08-19","cited_by_count":29,"area":null},{"id":"2108.06422","title":"Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models","created":"2021-08-13","cited_by_count":24,"area":null},{"id":"2206.14906","title":"A Best-of-Both-Worlds Algorithm for Bandits with Delayed Feedback","created":"2022-06-29","cited_by_count":23,"area":null},{"id":"2201.13172","title":"Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2022-01-31","cited_by_count":22,"area":null},{"id":"2211.16275","title":"A survey on multi-player bandits","created":"2022-11-29","cited_by_count":19,"area":null},{"id":"2111.01589","title":"Nonstochastic Bandits and Experts with Arm-Dependent Delays","created":"2021-11-02","cited_by_count":18,"area":null},{"id":"2112.02866","title":"Nonstochastic Bandits with Composite Anonymous Feedback","created":"2021-12-06","cited_by_count":16,"area":null},{"id":"2111.12482","title":"One More Step Towards Reality: Cooperative Bandits with Imperfect Communication","created":"2021-11-24","cited_by_count":15,"area":null},{"id":"2305.08629","title":"A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs","created":"2023-05-15","cited_by_count":15,"area":null},{"id":"2103.04550","title":"No Weighted-Regret Learning in Adversarial Bandits with Delays","created":"2021-03-08","cited_by_count":12,"area":null},{"id":"2308.10675","title":"A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays","created":"2023-08-21","cited_by_count":11,"area":null},{"id":"2205.14174","title":"Private and Byzantine-Proof Cooperative Decision-Making","created":"2022-05-27","cited_by_count":10,"area":null},{"id":"2110.04396","title":"When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Bandits","created":"2021-10-08","cited_by_count":8,"area":null},{"id":"2207.05827","title":"Differentially Private Linear Bandits with Partial Distributed Feedback","created":"2022-07-12","cited_by_count":8,"area":null},{"id":"2305.19036","title":"Delayed Bandits: When Do Intermediate Observations Help?","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2301.09223","title":"Doubly Adversarial Federated Bandits","created":"2023-01-22","cited_by_count":7,"area":null},{"id":"2301.10500","title":"Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning","created":"2023-01-25","cited_by_count":7,"area":null},{"id":"2302.07446","title":"On-Demand Communication for Asynchronous Multi-Agent Bandits","created":"2023-02-15","cited_by_count":7,"area":null},{"id":"2305.07911","title":"Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2023-05-13","cited_by_count":6,"area":null},{"id":"2408.15158","title":"Delay as Payoff in MAB","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2503.19856","title":"Capacity-Constrained Online Learning with Delays: Scheduling Frameworks and Regret Trade-offs","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2506.07595","title":"Exploiting Curvature in Online Convex Optimization with Delayed Feedback","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2106.04207","title":"Cooperative Stochastic Multi-agent Multi-armed Bandits Robust to Adversarial Corruptions","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2211.08980","title":"Asynchronous Gradient Play in Zero-Sum Multi-agent Games","created":"2022-11-16","cited_by_count":5,"area":null},{"id":"2510.09127","title":"Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2106.04982","title":"Cooperative Online Learning with Feedback Graphs","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2201.13170","title":"Cooperative Online Learning in Stochastic and Adversarial MDPs","created":"2022-01-31","cited_by_count":4,"area":null},{"id":"2405.16843","title":"Non-stochastic Bandits With Evolving Observations","created":"2024-05-27","cited_by_count":4,"area":null},{"id":"2106.03927","title":"Improving Social Welfare While Preserving Autonomy via a Pareto Mediator","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2211.17154","title":"On Regret-optimal Cooperative Nonstochastic Multi-armed Bandits","created":"2022-11-30","cited_by_count":3,"area":null},{"id":"2308.04314","title":"Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Constant Communication Costs","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2408.14603","title":"Biased Dueling Bandits with Stochastic Delayed Feedback","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2503.08004","title":"Multiplayer Information Asymmetric Bandits in Metric Spaces","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2503.08961","title":"Multiplayer Information Asymmetric Contextual Bandits","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2602.02634","title":"A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2110.07232","title":"Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-Fidelity Feedback","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2205.09056","title":"Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2302.06916","title":"Effective Dimension in Bandit Problems under Censorship","created":"2023-02-14","cited_by_count":2,"area":null},{"id":"2305.02527","title":"Reinforcement Learning with Delayed, Composite, and Partially Anonymous Reward","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2405.16168","title":"Multi-Player Approaches for Dueling Bandits","created":"2024-05-25","cited_by_count":2,"area":null},{"id":"2505.24193","title":"Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2601.07901","title":"Decentralized Online Convex Optimization with Unknown Feedback Delays","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2602.06902","title":"Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memory","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2110.13400","title":"Scale-Free Adversarial Multi-Armed Bandit with Arbitrary Feedback Delays","created":"2021-10-26","cited_by_count":1,"area":null},{"id":"2205.08234","title":"Delaytron: Efficient Learning of Multiclass Classifiers with Delayed Bandit Feedbacks","created":"2022-05-17","cited_by_count":1,"area":null},{"id":"2302.00814","title":"Stochastic Contextual Bandits with Long Horizon Rewards","created":"2023-02-02","cited_by_count":1,"area":null},{"id":"2307.09093","title":"Non-stationary Delayed Combinatorial Semi-Bandit with Causally Related Rewards","created":"2023-07-18","cited_by_count":1,"area":null},{"id":"2308.08046","title":"Regret Lower Bounds in Multi-agent Multi-armed Bandit","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2310.11188","title":"Adversarial Bandits with Multi-User Delayed Feedback: Theory and Application","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2310.17385","title":"Multitask Online Learning: Listen to the Neighborhood Buzz","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2409.19092","title":"Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2501.03132","title":"Communication Bounds for the Distributed Experts Problem","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2502.18709","title":"Bandit and Delayed Feedback in Online Structured Prediction","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2509.22426","title":"Learning from Delayed Feedback in Games via Extra Prediction","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.02149","title":"Reinforcement Learning with Action-Triggered Observations","created":"2025-10-02","cited_by_count":1,"area":"deeprl"},{"id":"2606.11711","title":"Capacity-Constrained Online Convex Optimization with Delayed Feedback","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2106.02855","title":"Multi-armed Bandit Algorithms on System-on-Chip: Go Frequentist or Bayesian?","created":"2021-06-05","cited_by_count":0,"area":null},{"id":"2106.03546","title":"On Learning to Rank Long Sequences with Contextual Bandits","created":"2021-06-07","cited_by_count":0,"area":null},{"id":"2111.10708","title":"PAC-Learning Uniform Ergodic Communicative Networks","created":"2021-11-21","cited_by_count":0,"area":null},{"id":"2301.11802","title":"Decentralized Online Bandit Optimization on Directed Graphs with Regret Bounds","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2306.08670","title":"Simple Opinion Dynamics for No-Regret Learning","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2601.12518","title":"Cooperative Multi-agent RL with Communication Constraints","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2602.06404","title":"Near-Optimal Regret for Distributed Adversarial Bandits: A Black-Box Approach","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.17486","title":"Linear Convergence in Games with Delayed Feedback via Extra Prediction","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2605.03493","title":"Bandits on graphs and structures","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.13145","title":"Collaborating in Multi-Armed Bandits with Strategic Agents","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.16656","title":"Near-Optimal Stochastic Linear Bandits with Delay","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.11873","title":"DCM Bandits: Multiplayer Information Asymmetric Cascading Bandits for Multiple Clicks","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.16216","title":"Beyond Peak Backlog: Conditional Energy and Temporal Geometry in Capacity-Constrained Delayed Bandit Optimization","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.01761","title":"Pooling and Drift in Delayed Bandits","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}