{"total":39,"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":"2105.08158","title":"The Confluence of Networks, Games and Learning","created":"2021-05-17","cited_by_count":26,"area":null},{"id":"2109.03699","title":"Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis","created":"2021-09-08","cited_by_count":26,"area":null},{"id":"2103.04972","title":"Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation","created":"2021-03-08","cited_by_count":23,"area":null},{"id":"2208.05925","title":"Near-Optimal Algorithms for Making the Gradient Small in Stochastic Minimax Optimization","created":"2022-08-11","cited_by_count":20,"area":null},{"id":"2112.13109","title":"Accelerated and instance-optimal policy evaluation with linear function approximation","created":"2021-12-24","cited_by_count":18,"area":null},{"id":"2106.01761","title":"Near Optimal Stochastic Algorithms for Finite-Sum Unbalanced Convex-Concave Minimax Optimization","created":"2021-06-03","cited_by_count":16,"area":null},{"id":"2106.06075","title":"A Decentralized Adaptive Momentum Method for Solving a Class of Min-Max Optimization Problems","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2310.20369","title":"Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm","created":"2023-10-31","cited_by_count":9,"area":null},{"id":"2109.04033","title":"New Versions of Gradient Temporal Difference Learning","created":"2021-09-09","cited_by_count":6,"area":null},{"id":"2110.05597","title":"Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees","created":"2021-10-11","cited_by_count":6,"area":null},{"id":"2203.00035","title":"Can Mean Field Control (MFC) Approximate Cooperative Multi Agent Reinforcement Learning (MARL) with Non-Uniform Interaction?","created":"2022-02-28","cited_by_count":6,"area":null},{"id":"2212.02387","title":"An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2103.13147","title":"Multi-Agent Off-Policy TD Learning: Finite-Time Analysis with Near-Optimal Sample Complexity and Communication Complexity","created":"2021-03-24","cited_by_count":5,"area":null},{"id":"2106.00543","title":"MARL with General Utilities via Decentralized Shadow Reward Actor-Critic","created":"2021-05-29","cited_by_count":5,"area":null},{"id":"2303.02532","title":"PRECISION: Decentralized Constrained Min-Max Learning with Low Communication and Sample Complexities","created":"2023-03-05","cited_by_count":5,"area":null},{"id":"2307.15868","title":"Faster Stochastic Algorithms for Minimax Optimization under Polyak--{\\L}ojasiewicz Conditions","created":"2023-07-29","cited_by_count":5,"area":null},{"id":"2410.09568","title":"Second-Order Min-Max Optimization with Lazy Hessians","created":"2024-10-12","cited_by_count":5,"area":null},{"id":"2403.15935","title":"Sample and Communication Efficient Fully Decentralized MARL Policy Evaluation via a New Approach: Local TD update","created":"2024-03-23","cited_by_count":4,"area":null},{"id":"2104.10601","title":"Statistical inference for generative adversarial networks and other minimax problems","created":"2021-04-21","cited_by_count":3,"area":null},{"id":"2202.05812","title":"Distributed saddle point problems for strongly concave-convex functions","created":"2022-02-11","cited_by_count":3,"area":null},{"id":"2402.06501","title":"Scalable Interactive Machine Learning for Future Command and Control","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2110.05125","title":"Non-Parametric Neuro-Adaptive Coordination of Multi-Agent Systems","created":"2021-10-11","cited_by_count":1,"area":null},{"id":"2110.12929","title":"Convergence Rates of Average-Reward Multi-agent Reinforcement Learning via Randomized Linear Programming","created":"2021-10-22","cited_by_count":1,"area":null},{"id":"2110.15092","title":"A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning","created":"2021-10-27","cited_by_count":1,"area":null},{"id":"2111.12961","title":"Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning","created":"2021-11-25","cited_by_count":1,"area":null},{"id":"2111.15087","title":"MAMRL: Exploiting Multi-agent Meta Reinforcement Learning in WAN Traffic Engineering","created":"2021-11-30","cited_by_count":1,"area":null},{"id":"2202.13863","title":"Provably Efficient Convergence of Primal-Dual Actor-Critic with Nonlinear Function Approximation","created":"2022-02-28","cited_by_count":1,"area":null},{"id":"2310.00638","title":"A primal-dual perspective for distributed TD-learning","created":"2023-10-01","cited_by_count":1,"area":null},{"id":"2211.01266","title":"Knowing the Past to Predict the Future: Reinforcement Virtual Learning","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2305.15643","title":"Federated Composite Saddle Point Optimization","created":"2023-05-25","cited_by_count":0,"area":null},{"id":"2306.02766","title":"Networked Communication for Decentralised Agents in Mean-Field Games","created":"2023-06-05","cited_by_count":0,"area":null},{"id":"2307.16706","title":"Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes","created":"2023-07-31","cited_by_count":0,"area":null},{"id":"2309.00997","title":"Switch and Conquer: Efficient Algorithms By Switching Stochastic Gradient Oracles For Decentralized Saddle Point Problems","created":"2023-09-02","cited_by_count":0,"area":null},{"id":"2407.02613","title":"Wildfire Autonomous Response and Prediction Using Cellular Automata (WARP-CA)","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2505.18433","title":"Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2602.01339","title":"Finding Differentially Private Second Order Stationary Points in Stochastic Minimax Optimization","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2605.01701","title":"Stability and Generalization for Decentralized Markov SGD","created":"2026-05-03","cited_by_count":0,"area":null}],"next_cursor":null}