{"total":14,"rows":[{"id":"2211.03464","title":"A Survey on Quantum Reinforcement Learning","created":"2022-11-07","cited_by_count":53,"area":null},{"id":"2301.05096","title":"Asynchronous training of quantum reinforcement learning","created":"2023-01-12","cited_by_count":20,"area":null},{"id":"2212.09328","title":"Quantum policy gradient algorithms","created":"2022-12-19","cited_by_count":15,"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":"2404.10017","title":"Model-based Offline Quantum Reinforcement Learning","created":"2024-04-14","cited_by_count":4,"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":"2502.14467","title":"Provable Quantum Algorithm Advantage for Gaussian Process Quadrature","created":"2025-02-20","cited_by_count":3,"area":null},{"id":"2304.09648","title":"Quantum deep Q learning with distributed prioritized experience replay","created":"2023-04-19","cited_by_count":2,"area":null},{"id":"2502.13755","title":"GPA: Grover Policy Agent for Generating Optimal Quantum Sensor Circuits","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2411.01391","title":"Differentiable Quantum Computing for Large-scale Linear Control","created":"2024-11-03","cited_by_count":0,"area":null},{"id":"2508.21246","title":"HCQA: Hybrid Classical-Quantum Agent for Generating Optimal Quantum Sensor Circuits","created":"2025-08-28","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":"2607.11936","title":"Qubit-Efficient Quantum Search for Hyperdimensional Decomposition via Logarithmic Encoding","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2609.05842","title":"Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference","created":"2026-09-05","cited_by_count":0,"area":null}],"next_cursor":null}