{"total":38,"rows":[{"id":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124,"area":null},{"id":"2102.03758","title":"Non-stationary Online Learning with Memory and Non-stochastic Control","created":"2021-02-07","cited_by_count":33,"area":null},{"id":"2102.06933","title":"Revisiting Smoothed Online Learning","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2207.03106","title":"A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits","created":"2022-07-07","cited_by_count":28,"area":null},{"id":"2102.13028","title":"Batched Neural Bandits","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2102.09864","title":"An Algorithm for Stochastic and Adversarial Bandits with Switching Costs","created":"2021-02-19","cited_by_count":19,"area":null},{"id":"2205.13451","title":"Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback","created":"2022-05-26","cited_by_count":17,"area":null},{"id":"2102.03803","title":"Lazy OCO: Online Convex Optimization on a Switching Budget","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2206.03098","title":"Better Best of Both Worlds Bounds for Bandits with Switching Costs","created":"2022-06-07","cited_by_count":13,"area":null},{"id":"2110.08057","title":"Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits","created":"2021-10-15","cited_by_count":9,"area":null},{"id":"2202.07079","title":"Synthetically Controlled Bandits","created":"2022-02-14","cited_by_count":8,"area":null},{"id":"2103.11370","title":"Online Convex Optimization with Continuous Switching Constraint","created":"2021-03-21","cited_by_count":6,"area":null},{"id":"2302.04374","title":"Near-Optimal Adversarial Reinforcement Learning with Switching Costs","created":"2023-02-08","cited_by_count":4,"area":null},{"id":"2203.15236","title":"Best Arm Identification in Restless Markov Multi-Armed Bandits","created":"2022-03-29","cited_by_count":3,"area":null},{"id":"2204.11174","title":"Complete Policy Regret Bounds for Tallying Bandits","created":"2022-04-24","cited_by_count":3,"area":null},{"id":"2209.09419","title":"Multi-armed Bandit Learning on a Graph","created":"2022-09-20","cited_by_count":3,"area":null},{"id":"2303.01709","title":"Streaming Algorithms for Learning with Experts: Deterministic Versus Robust","created":"2023-03-03","cited_by_count":3,"area":null},{"id":"2405.20028","title":"A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2411.00707","title":"Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2305.02955","title":"Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2506.05479","title":"Learning-Augmented Algorithms for MTS with Bandit Access to Multiple Predictors","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2510.02820","title":"Online Learning in the Random Order Model","created":"2025-10-03","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":"2111.02024","title":"Learning in Online MDPs: Is there a Price for Handling the Communicating Case?","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2204.12764","title":"Bounded Memory Adversarial Bandits with Composite Anonymous Delayed Feedback","created":"2022-04-27","cited_by_count":1,"area":null},{"id":"2604.11328","title":"Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2107.05289","title":"Continuous Time Bandits With Sampling Costs","created":"2021-07-12","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":"2404.01883","title":"Adversarial Combinatorial Bandits with Switching Costs","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2410.14533","title":"The Traveling Bandit: A Framework for Bayesian Optimization with Movement Costs","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2512.11131","title":"Fairness-Regularized Online Optimization with Switching Costs","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2603.00803","title":"Lookahead identification in adversarial bandits: accuracy and memory bounds","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2606.02363","title":"Minimax-Optimal Policy Regret in Partially Observable Markov Games","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.03851","title":"Two-Action Apple Tasting with Switching Costs","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.27448","title":"Learning in Markovian bandits with non-observable states and constrained decision epochs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.10571","title":"Learning from Local Walks on Dynamic Graphs with Bandit Feedback","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2608.09366","title":"Beyond Binary: Continuous State Optimization with Graph-Structured Objectives","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2610.14790","title":"Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}