{"total":163,"rows":[{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114,"area":null},{"id":"2111.12444","title":"Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications","created":"2021-11-24","cited_by_count":97,"area":null},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2101.05436","title":"Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates","created":"2021-01-14","cited_by_count":74,"area":null},{"id":"2108.08612","title":"Settling the Variance of Multi-Agent Policy Gradients","created":"2021-08-19","cited_by_count":45,"area":null},{"id":"2110.05707","title":"On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning","created":"2021-10-12","cited_by_count":36,"area":null},{"id":"2510.17845","title":"MAT-Agent: Adaptive Multi-Agent Training Optimization","created":"2025-10-10","cited_by_count":35,"area":null},{"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":"2110.13484","title":"Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey","created":"2021-10-26","cited_by_count":34,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2105.08692","title":"Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition","created":"2021-05-18","cited_by_count":30,"area":null},{"id":"2312.05162","title":"A Review of Cooperation in Multi-agent Learning","created":"2023-12-08","cited_by_count":29,"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":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2102.00582","title":"Multi-Agent Reinforcement Learning with Temporal Logic Specifications","created":"2021-02-01","cited_by_count":27,"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":"2205.15023","title":"Scalable Multi-Agent Model-Based Reinforcement Learning","created":"2022-05-25","cited_by_count":25,"area":null},{"id":"2105.03363","title":"Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts","created":"2021-05-07","cited_by_count":24,"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":"2204.06127","title":"Reinforcement learning on graphs: A survey","created":"2022-04-13","cited_by_count":20,"area":null},{"id":"2211.17116","title":"Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning","created":"2022-11-30","cited_by_count":20,"area":null},{"id":"2105.01798","title":"Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence","created":"2021-05-04","cited_by_count":18,"area":null},{"id":"2107.01151","title":"Collaborative Visual Navigation","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2103.06967","title":"Adversarial attacks in consensus-based multi-agent reinforcement learning","created":"2021-03-11","cited_by_count":17,"area":null},{"id":"2107.08622","title":"Provably Efficient Multi-Task Reinforcement Learning with Model Transfer","created":"2021-07-19","cited_by_count":16,"area":null},{"id":"2107.14316","title":"Survey of Recent Multi-Agent Reinforcement Learning Algorithms Utilizing Centralized Training","created":"2021-07-29","cited_by_count":16,"area":null},{"id":"2111.06721","title":"Causal Multi-Agent Reinforcement Learning: Review and Open Problems","created":"2021-11-12","cited_by_count":16,"area":null},{"id":"2204.03516","title":"Distributed Reinforcement Learning for Robot Teams: A Review","created":"2022-04-07","cited_by_count":16,"area":null},{"id":"2210.08857","title":"On the convergence of policy gradient methods to Nash equilibria in general stochastic games","created":"2022-10-17","cited_by_count":16,"area":null},{"id":"2304.08349","title":"Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach","created":"2023-04-17","cited_by_count":15,"area":null},{"id":"2105.08601","title":"Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection","created":"2021-05-18","cited_by_count":14,"area":null},{"id":"2201.08484","title":"Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming","created":"2022-01-20","cited_by_count":14,"area":null},{"id":"2209.03859","title":"A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning","created":"2022-09-08","cited_by_count":14,"area":null},{"id":"2208.01682","title":"Heterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative MARL","created":"2022-08-02","cited_by_count":12,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2102.10740","title":"Communication Efficient Parallel Reinforcement Learning","created":"2021-02-22","cited_by_count":10,"area":null},{"id":"2307.09470","title":"Multi-Player Zero-Sum Markov Games with Networked Separable Interactions","created":"2023-07-13","cited_by_count":10,"area":null},{"id":"2112.06127","title":"Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings","created":"2021-11-25","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":"2308.11272","title":"FoX: Formation-aware exploration in multi-agent reinforcement learning","created":"2023-08-22","cited_by_count":9,"area":null},{"id":"2501.13200","title":"SRMT: Shared Memory for Multi-agent Lifelong Pathfinding","created":"2025-01-22","cited_by_count":8,"area":null},{"id":"2102.06042","title":"Modeling the Interaction between Agents in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-10","cited_by_count":7,"area":null},{"id":"2110.00096","title":"Decentralized Graph-Based Multi-Agent Reinforcement Learning Using Reward Machines","created":"2021-09-30","cited_by_count":7,"area":null},{"id":"2206.07642","title":"Convergence and Price of Anarchy Guarantees of the Softmax Policy Gradient in Markov Potential Games","created":"2022-06-15","cited_by_count":7,"area":null},{"id":"2207.06559","title":"Scalable Model-based Policy Optimization for Decentralized Networked Systems","created":"2022-07-13","cited_by_count":7,"area":null},{"id":"2212.02376","title":"DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization","created":"2022-12-05","cited_by_count":7,"area":null},{"id":"2305.17342","title":"Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL","created":"2023-05-27","cited_by_count":7,"area":null},{"id":"2307.03119","title":"Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2502.19717","title":"Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2104.09402","title":"Agent-Centric Representations for Multi-Agent Reinforcement Learning","created":"2021-04-19","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":"2112.02813","title":"MDPGT: Momentum-based Decentralized Policy Gradient Tracking","created":"2021-12-06","cited_by_count":6,"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":"2308.01649","title":"MARLIM: Multi-Agent Reinforcement Learning for Inventory Management","created":"2023-08-03","cited_by_count":6,"area":null},{"id":"2402.02097","title":"Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing","created":"2024-02-03","cited_by_count":6,"area":null},{"id":"2406.06823","title":"Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies","created":"2024-06-10","cited_by_count":6,"area":null},{"id":"2504.15425","title":"Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL","created":"2025-04-21","cited_by_count":6,"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":"2110.07392","title":"Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2110.13621","title":"Model-based Reinforcement Learning for Service Mesh Fault Resiliency in a Web Application-level","created":"2021-10-21","cited_by_count":5,"area":null},{"id":"2112.08702","title":"Learning to Share in Multi-Agent Reinforcement Learning","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2202.09422","title":"Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games","created":"2022-02-18","cited_by_count":5,"area":null},{"id":"2209.08244","title":"MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning","created":"2022-09-17","cited_by_count":5,"area":null},{"id":"2211.03032","title":"Decentralized Policy Optimization","created":"2022-11-06","cited_by_count":5,"area":null},{"id":"2212.07684","title":"Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2304.10351","title":"Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2306.06236","title":"iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2306.08419","title":"Mediated Multi-Agent Reinforcement Learning","created":"2023-06-14","cited_by_count":5,"area":null},{"id":"2401.04934","title":"Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey","created":"2024-01-10","cited_by_count":5,"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":"2109.11692","title":"Dimension-Free Rates for Natural Policy Gradient in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":4,"area":null},{"id":"2201.13170","title":"Cooperative Online Learning in Stochastic and Adversarial MDPs","created":"2022-01-31","cited_by_count":4,"area":null},{"id":"2210.00882","title":"MSRL: Distributed Reinforcement Learning with Dataflow Fragments","created":"2022-10-03","cited_by_count":4,"area":null},{"id":"2302.01188","title":"Best Possible Q-Learning","created":"2023-02-02","cited_by_count":4,"area":null},{"id":"2311.15594","title":"Networked Multiagent Safe Reinforcement Learning for Low-carbon Demand Management in Distribution Network","created":"2023-11-27","cited_by_count":4,"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":"2405.13205","title":"Multi-Agent Reinforcement Learning with Hierarchical Coordination for Emergency Responder Stationing","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2509.16606","title":"Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learning","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2509.20648","title":"Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2301.04299","title":"SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning","created":"2023-01-11","cited_by_count":3,"area":null},{"id":"2404.16388","title":"SwarmRL: Building the Future of Smart Active Systems","created":"2024-04-25","cited_by_count":3,"area":null},{"id":"2405.19811","title":"Approximate Global Convergence of Independent Learning in Multi-Agent Systems","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2409.12882","title":"On the Hardness of Decentralized Multi-Agent Policy Evaluation under Byzantine Attacks","created":"2024-09-19","cited_by_count":3,"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":"2508.07001","title":"Consensus-based Decentralized Multi-agent Reinforcement Learning for Random Access Network Optimization","created":"2025-08-09","cited_by_count":3,"area":null},{"id":"2102.09745","title":"Decentralized Deterministic Multi-Agent Reinforcement Learning","created":"2021-02-19","cited_by_count":2,"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":"2109.01654","title":"Multi-agent Natural Actor-critic Reinforcement Learning Algorithms","created":"2021-09-03","cited_by_count":2,"area":null},{"id":"2111.00438","title":"Decentralized Multi-Agent Reinforcement Learning: An Off-Policy Method","created":"2021-10-31","cited_by_count":2,"area":null},{"id":"2201.04962","title":"Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph","created":"2022-01-10","cited_by_count":2,"area":null},{"id":"2212.06357","title":"Scalable and Sample Efficient Distributed Policy Gradient Algorithms in Multi-Agent Networked Systems","created":"2022-12-13","cited_by_count":2,"area":null},{"id":"2311.03756","title":"Learning Decentralized Traffic Signal Controllers with Multi-Agent Graph Reinforcement Learning","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2311.12613","title":"Decentralised Q-Learning for Multi-Agent Markov Decision Processes with a Satisfiability Criterion","created":"2023-11-21","cited_by_count":2,"area":null},{"id":"2312.12067","title":"Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence Beyond the Minty Property","created":"2023-12-19","cited_by_count":2,"area":null},{"id":"2404.13348","title":"Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systems","created":"2024-04-20","cited_by_count":2,"area":null},{"id":"2502.15425","title":"TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2109.02032","title":"Soft Hierarchical Graph Recurrent Networks for Many-Agent Partially Observable Environments","created":"2021-09-05","cited_by_count":1,"area":null},{"id":"2110.12306","title":"Fully Distributed Actor-Critic Architecture for Multitask Deep Reinforcement Learning","created":"2021-10-23","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}],"next_cursor":"100"}