{"total":121,"rows":[{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57,"area":null},{"id":"2102.04402","title":"Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning","created":"2021-02-08","cited_by_count":56,"area":null},{"id":"2409.03052","title":"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning","created":"2024-09-04","cited_by_count":50,"area":null},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2108.01832","title":"Offline Decentralized Multi-Agent Reinforcement Learning","created":"2021-08-04","cited_by_count":33,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2103.03216","title":"Continuous Coordination As a Realistic Scenario for Lifelong Learning","created":"2021-03-04","cited_by_count":32,"area":null},{"id":"2106.08315","title":"Decentralized Local Stochastic Extra-Gradient for Variational Inequalities","created":"2021-06-15","cited_by_count":25,"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":"2311.01753","title":"RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization","created":"2023-11-03","cited_by_count":20,"area":null},{"id":"2110.05769","title":"Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2211.02147","title":"A Survey on Reinforcement Learning in Aviation Applications","created":"2022-11-03","cited_by_count":19,"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":"2107.14316","title":"Survey of Recent Multi-Agent Reinforcement Learning Algorithms Utilizing Centralized Training","created":"2021-07-29","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":"2205.02453","title":"Learning to Solve Vehicle Routing Problems: A Survey","created":"2022-05-05","cited_by_count":16,"area":null},{"id":"2110.03313","title":"Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees","created":"2021-10-07","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":"2202.02771","title":"Optimal Algorithms for Decentralized Stochastic Variational Inequalities","created":"2022-02-06","cited_by_count":14,"area":null},{"id":"2305.15938","title":"First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2302.02792","title":"Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning","created":"2023-02-06","cited_by_count":13,"area":null},{"id":"2109.12343","title":"Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems","created":"2021-09-25","cited_by_count":12,"area":null},{"id":"2212.12978","title":"Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization","created":"2022-12-26","cited_by_count":12,"area":null},{"id":"2103.12710","title":"Spatial Intention Maps for Multi-Agent Mobile Manipulation","created":"2021-03-23","cited_by_count":11,"area":null},{"id":"2304.14656","title":"From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL","created":"2023-04-28","cited_by_count":11,"area":null},{"id":"2109.09531","title":"Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge","created":"2021-09-20","cited_by_count":10,"area":null},{"id":"2208.13592","title":"Smooth Monotone Stochastic Variational Inequalities and Saddle Point Problems: A Survey","created":"2022-08-29","cited_by_count":10,"area":null},{"id":"2305.00135","title":"Joint Sensing, Communication, and AI: A Trifecta for Resilient THz User Experiences","created":"2023-04-29","cited_by_count":10,"area":null},{"id":"2408.14597","title":"On Centralized Critics in Multi-Agent Reinforcement Learning","created":"2024-08-26","cited_by_count":10,"area":null},{"id":"2206.01132","title":"A Communication-efficient Algorithm with Linear Convergence for Federated Minimax Learning","created":"2022-06-02","cited_by_count":9,"area":null},{"id":"2305.13030","title":"Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations","created":"2023-05-22","cited_by_count":9,"area":null},{"id":"2112.13826","title":"Last-Iterate Convergence of Saddle-Point Optimizers via High-Resolution Differential Equations","created":"2021-12-27","cited_by_count":8,"area":null},{"id":"2207.14561","title":"Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization","created":"2022-07-29","cited_by_count":8,"area":null},{"id":"2102.11386","title":"Direct-Search for a Class of Stochastic Min-Max Problems","created":"2021-02-22","cited_by_count":7,"area":null},{"id":"2302.07615","title":"Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities","created":"2023-02-15","cited_by_count":7,"area":null},{"id":"2108.12988","title":"Learning Meta Representations for Agents in Multi-Agent Reinforcement Learning","created":"2021-08-30","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":"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":"2307.13957","title":"Heterogeneous Embodied Multi-Agent Collaboration","created":"2023-07-26","cited_by_count":6,"area":null},{"id":"2403.15341","title":"Collaborative AI Teaming in Unknown Environments via Active Goal Deduction","created":"2024-03-22","cited_by_count":6,"area":null},{"id":"2103.13026","title":"The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communication","created":"2021-03-24","cited_by_count":5,"area":null},{"id":"2104.10917","title":"Independent Reinforcement Learning for Weakly Cooperative Multiagent Traffic Control Problem","created":"2021-04-22","cited_by_count":5,"area":null},{"id":"2202.06255","title":"Strategy Synthesis for Zero-Sum Neuro-Symbolic Concurrent Stochastic Games","created":"2022-02-13","cited_by_count":5,"area":null},{"id":"2204.12937","title":"Learning to Transfer Role Assignment Across Team Sizes","created":"2022-04-17","cited_by_count":5,"area":null},{"id":"2207.02249","title":"Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning","created":"2022-07-05","cited_by_count":5,"area":null},{"id":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2305.18875","title":"Centralised rehearsal of decentralised cooperation: Multi-agent reinforcement learning for the scalable coordination of residential energy flexibility","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2502.04773","title":"An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks","created":"2025-02-07","cited_by_count":5,"area":null},{"id":"2606.02859","title":"Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions","created":"2026-06-01","cited_by_count":5,"area":null},{"id":"2106.07289","title":"Decentralized Personalized Federated Learning for Min-Max Problems","created":"2021-06-14","cited_by_count":4,"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":"2203.15500","title":"An Unbiased Symmetric Matrix Estimator for Topology Inference under Partial Observability","created":"2022-03-29","cited_by_count":4,"area":null},{"id":"2207.05886","title":"Reward-Sharing Relational Networks in Multi-Agent Reinforcement Learning as a Framework for Emergent Behavior","created":"2022-07-12","cited_by_count":4,"area":null},{"id":"2311.01953","title":"Optimistic Multi-Agent Policy Gradient","created":"2023-11-03","cited_by_count":4,"area":null},{"id":"2311.11280","title":"Multi-Timescale Control and Communications with Deep Reinforcement Learning -- Part II: Control-Aware Radio Resource Allocation","created":"2023-11-19","cited_by_count":4,"area":null},{"id":"2502.05573","title":"Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning","created":"2025-02-08","cited_by_count":4,"area":null},{"id":"2102.05026","title":"Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies","created":"2021-02-09","cited_by_count":3,"area":null},{"id":"2108.04087","title":"Reinforcement Learning for Intelligent Healthcare Systems: A Comprehensive Survey","created":"2021-08-05","cited_by_count":3,"area":null},{"id":"2110.08642","title":"Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning","created":"2021-10-16","cited_by_count":3,"area":null},{"id":"2203.08454","title":"Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agents","created":"2022-03-16","cited_by_count":3,"area":null},{"id":"2206.10575","title":"Solving Constrained Variational Inequalities via a First-order Interior Point-based Method","created":"2022-06-21","cited_by_count":3,"area":null},{"id":"2210.05367","title":"Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2210.06274","title":"Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning","created":"2022-10-12","cited_by_count":3,"area":null},{"id":"2304.10317","title":"Adaptive Consensus Optimization Method for GANs","created":"2023-04-20","cited_by_count":3,"area":null},{"id":"2408.13567","title":"Hybrid Training for Enhanced Multi-task Generalization in Multi-agent Reinforcement Learning","created":"2024-08-24","cited_by_count":3,"area":null},{"id":"2504.03069","title":"Properties of Fixed Points of Generalised Extra Gradient Methods Applied to Min-Max Problems","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2602.15776","title":"GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2106.02540","title":"Transferable and Distributed User Association Policies for 5G and Beyond Networks","created":"2021-06-04","cited_by_count":2,"area":null},{"id":"2111.11229","title":"Off-Policy Correction For Multi-Agent Reinforcement Learning","created":"2021-11-22","cited_by_count":2,"area":null},{"id":"2201.12718","title":"Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning","created":"2022-01-30","cited_by_count":2,"area":null},{"id":"2202.06460","title":"Simultaneous Transport Evolution for Minimax Equilibria on Measures","created":"2022-02-14","cited_by_count":2,"area":null},{"id":"2204.10063","title":"Resilient robot teams: a review integrating decentralised control, change-detection, and learning","created":"2022-04-21","cited_by_count":2,"area":null},{"id":"2212.07967","title":"Distributed-Training-and-Execution Multi-Agent Reinforcement Learning for Power Control in HetNet","created":"2022-12-15","cited_by_count":2,"area":null},{"id":"2303.00970","title":"PAPAL: A Provable PArticle-based Primal-Dual ALgorithm for Mixed Nash Equilibrium","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2304.08769","title":"Cooperative Multi-Agent Reinforcement Learning for Inventory Management","created":"2023-04-18","cited_by_count":2,"area":null},{"id":"2311.11281","title":"Multi-Timescale Control and Communications with Deep Reinforcement Learning -- Part I: Communication-Aware Vehicle Control","created":"2023-11-19","cited_by_count":2,"area":null},{"id":"2405.01839","title":"SocialGFs: Learning Social Gradient Fields for Multi-Agent Reinforcement Learning","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2503.01440","title":"Trajectory-Class-Aware Multi-Agent Reinforcement Learning","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2503.04262","title":"Guidelines for Applying RL and MARL in Cybersecurity Applications","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2509.25550","title":"Unifying Agent Interaction and World Information for Multi-agent Coordination","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2103.02150","title":"Inference-Based Deterministic Messaging For Multi-Agent Communication","created":"2021-03-03","cited_by_count":1,"area":null},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"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":"2202.00531","title":"PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent","created":"2022-02-01","cited_by_count":1,"area":null},{"id":"2202.05135","title":"Group-Agent Reinforcement Learning","created":"2022-02-10","cited_by_count":1,"area":null},{"id":"2206.05733","title":"Finite-Time Analysis of Fully Decentralized Single-Timescale Actor-Critic","created":"2022-06-12","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":"2306.02430","title":"A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning","created":"2023-06-04","cited_by_count":1,"area":null},{"id":"2308.09219","title":"Learning in Cooperative Multiagent Systems Using Cognitive and Machine Models","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2308.14971","title":"Distributed multi-agent target search and tracking with Gaussian process and reinforcement learning","created":"2023-08-29","cited_by_count":1,"area":null},{"id":"2310.04623","title":"Deconstructing Cooperation and Ostracism via Multi-Agent Reinforcement Learning","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2410.05942","title":"Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2507.01932","title":"A first-order method for nonconvex-nonconcave minimax problems under a local Kurdyka-Lojasiewicz condition","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2507.09495","title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2511.02304","title":"Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2603.01430","title":"On the Stability Connection Between Discrete-Time Algorithms and Their Resolution ODEs: Applications to Min-Max Optimisation","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2103.09520","title":"Decentralized Reinforcement Learning for Multi-Target Search and Detection by a Team of Drones","created":"2021-03-17","cited_by_count":0,"area":null},{"id":"2202.09859","title":"Cooperative Artificial Intelligence","created":"2022-02-20","cited_by_count":0,"area":null}],"next_cursor":"100"}