{"total":18,"rows":[{"id":"2212.12923","title":"Linear Combinatorial Semi-Bandit with Causally Related Rewards","created":"2022-12-25","cited_by_count":4,"area":null},{"id":"2302.05257","title":"Piecewise-Stationary Multi-Objective Multi-Armed Bandit with Application to Joint Communications and Sensing","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2502.04021","title":"Variational Quantum Optimization with Continuous Bandits","created":"2025-02-06","cited_by_count":2,"area":null},{"id":"2203.14572","title":"Distributed Task Management in Fog Computing: A Socially Concave Bandit Game","created":"2022-03-28","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":"2307.14138","title":"Piecewise-Stationary Combinatorial Semi-Bandit with Causally Related Rewards","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2308.16889","title":"Federated Learning in UAV-Enhanced Networks: Joint Coverage and Convergence Time Optimization","created":"2023-08-31","cited_by_count":1,"area":null},{"id":"2405.09528","title":"Energy-Efficient Sleep Mode Optimization of 5G mmWave Networks Using Deep Contextual MAB","created":"2024-05-15","cited_by_count":1,"area":null},{"id":"2510.12152","title":"Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2105.05564","title":"A Survey on Reinforcement Learning-Aided Caching in Mobile Edge Networks","created":"2021-05-12","cited_by_count":0,"area":null},{"id":"2202.03167","title":"Bayesian Non-stationary Linear Bandits for Large-Scale Recommender Systems","created":"2022-02-07","cited_by_count":0,"area":null},{"id":"2202.11699","title":"Exploiting Side Information for Improved Online Learning Algorithms in Wireless Networks","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2212.09926","title":"Bandit approach to conflict-free multi-agent Q-learning in view of photonic implementation","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2305.19161","title":"Cooperative Thresholded Lasso for Sparse Linear Bandit","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2307.09388","title":"Online Learning with Costly Features in Non-stationary Environments","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2401.10204","title":"Maximal-Capacity Discrete Memoryless Channel Identification","created":"2024-01-18","cited_by_count":0,"area":null},{"id":"2411.05661","title":"Multi-armed Bandits with Missing Outcome","created":"2024-11-08","cited_by_count":0,"area":null},{"id":"2511.22105","title":"Energy Efficient Sleep Mode Optimization in 5G mmWave Networks via Multi Agent Deep Reinforcement Learning","created":"2025-11-27","cited_by_count":0,"area":null}],"next_cursor":null}