{"total":27,"rows":[{"id":"2106.00198","title":"Gradient play in stochastic games: stationary points, convergence, and sample complexity","created":"2021-06-01","cited_by_count":34,"area":null},{"id":"2108.02731","title":"Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach","created":"2021-08-05","cited_by_count":28,"area":null},{"id":"2101.01041","title":"Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity","created":"2021-01-04","cited_by_count":15,"area":null},{"id":"2405.15861","title":"Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2302.13144","title":"Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient","created":"2023-02-25","cited_by_count":10,"area":null},{"id":"2301.12624","title":"Learning the Kalman Filter with Fine-Grained Sample Complexity","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2110.07112","title":"On the Sample Complexity of Decentralized Linear Quadratic Regulator with Partially Nested Information Structure","created":"2021-10-14","cited_by_count":7,"area":null},{"id":"2210.11577","title":"Global Convergence of Direct Policy Search for State-Feedback $\\mathcal{H}_\\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential","created":"2022-10-20","cited_by_count":7,"area":null},{"id":"2202.13046","title":"Distributed Multi-Agent Reinforcement Learning Based on Graph-Induced Local Value Functions","created":"2022-02-26","cited_by_count":6,"area":null},{"id":"2209.07883","title":"Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization","created":"2022-09-16","cited_by_count":6,"area":null},{"id":"2210.04810","title":"Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies","created":"2022-10-10","cited_by_count":6,"area":null},{"id":"2309.14648","title":"Learning the Uncertainty Sets for Control Dynamics via Set Membership: A Non-Asymptotic Analysis","created":"2023-09-26","cited_by_count":6,"area":null},{"id":"2311.18736","title":"Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms","created":"2023-11-30","cited_by_count":6,"area":null},{"id":"2107.12416","title":"Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent","created":"2021-07-26","cited_by_count":4,"area":null},{"id":"2309.04272","title":"Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence","created":"2023-09-08","cited_by_count":4,"area":null},{"id":"2309.04831","title":"Global Convergence of Receding-Horizon Policy Search in Learning Estimator Designs","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2410.17221","title":"Scalable spectral representations for multi-agent reinforcement learning in network MDPs","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2108.07970","title":"Scalable regret for learning to control network-coupled subsystems with unknown dynamics","created":"2021-08-18","cited_by_count":2,"area":null},{"id":"2406.00234","title":"Learning to Stabilize Unknown LTI Systems on a Single Trajectory under Stochastic Noise","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2210.08886","title":"Learning Decentralized Linear Quadratic Regulators with $\\sqrt{T}$ Regret","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2302.04151","title":"Policy Evaluation in Decentralized POMDPs with Belief Sharing","created":"2023-02-08","cited_by_count":1,"area":null},{"id":"2303.13657","title":"Policy Evaluation in Distributional LQR","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2311.11151","title":"On the Hardness of Learning to Stabilize Linear Systems","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2205.04855","title":"Secure Distributed/Federated Learning: Prediction-Privacy Trade-Off for Multi-Agent System","created":"2022-04-24","cited_by_count":0,"area":null},{"id":"2406.11168","title":"Two-Timescale Optimization Framework for Sparse-Feedback Linear-Quadratic Optimal Control","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2507.19895","title":"Douglas-Rachford Splitting for Group-Sparse Feedback Linear-Quadratic Control","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2510.09937","title":"Structured Cooperative Multi-Agent Reinforcement Learning: a Bayesian Network Perspective","created":"2025-10-11","cited_by_count":0,"area":null}],"next_cursor":null}