{"total":21,"rows":[{"id":"2211.03464","title":"A Survey on Quantum Reinforcement Learning","created":"2022-11-07","cited_by_count":53,"area":null},{"id":"2112.08451","title":"Quantum Algorithms for Reinforcement Learning with a Generative Model","created":"2021-12-15","cited_by_count":24,"area":null},{"id":"2205.14988","title":"Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets","created":"2022-05-30","cited_by_count":19,"area":null},{"id":"2212.09328","title":"Quantum policy gradient algorithms","created":"2022-12-19","cited_by_count":15,"area":null},{"id":"2310.05373","title":"Quantum Bayesian Optimization","created":"2023-10-09","cited_by_count":12,"area":null},{"id":"2302.10796","title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret","created":"2023-02-21","cited_by_count":9,"area":null},{"id":"2301.09680","title":"Quantum Heavy-tailed Bandits","created":"2023-01-23","cited_by_count":8,"area":null},{"id":"2302.08617","title":"Quantum Computing Provides Exponential Regret Improvement in Episodic Reinforcement Learning","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2301.13524","title":"Quantum contextual bandits and recommender systems for quantum data","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2504.02251","title":"Quantum Lipschitz Bandits","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2301.08544","title":"Multi-Armed Bandits and Quantum Channel Oracles","created":"2023-01-20","cited_by_count":3,"area":null},{"id":"2310.11684","title":"Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes","created":"2023-10-18","cited_by_count":3,"area":null},{"id":"2507.04438","title":"Quantum Algorithms for Bandits with Knapsacks with Improved Regret and Time Complexities","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2511.01253","title":"Quantum Deep Learning Still Needs a Quantum Leap","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2507.08543","title":"Quantum Algorithms for Projection-Free Sparse Convex Optimization","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2509.05890","title":"Quantum spatial best-arm identification via quantum walks","created":"2025-09-07","cited_by_count":0,"area":null},{"id":"2509.07633","title":"Variational Quantum Circuits in Offline Contextual Bandit Problems","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2603.18431","title":"Towards Noise-Resilient Quantum Multi-Armed and Stochastic Linear Bandits","created":"2026-03-19","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":"2608.14319","title":"Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.33132","title":"Quantum Monte Carlo Tree Search with Fixed Confidence","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}