{"total":155,"rows":[{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237,"area":"agents"},{"id":"2308.11339","title":"ProAgent: Building Proactive Cooperative Agents with Large Language Models","created":"2023-08-22","cited_by_count":98,"area":"agents"},{"id":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91,"area":"diffusion"},{"id":"2305.17330","title":"MADiff: Offline Multi-agent Learning with Diffusion Models","created":"2023-05-27","cited_by_count":75,"area":"diffusion"},{"id":"2305.19923","title":"MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL","created":"2023-05-31","cited_by_count":68,"area":"diffusion"},{"id":"2504.16129","title":"MARFT: Multi-Agent Reinforcement Fine-Tuning","created":"2025-04-21","cited_by_count":52,"area":"agents"},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2404.10775","title":"COMBO: Compositional World Models for Embodied Multi-Agent Cooperation","created":"2024-04-16","cited_by_count":49,"area":"wm"},{"id":"2405.08550","title":"Learning Multi-Agent Communication from Graph Modeling Perspective","created":"2024-05-14","cited_by_count":48,"area":null},{"id":"2502.14743","title":"Multi-Agent Coordination across Diverse Applications: A Survey","created":"2025-02-20","cited_by_count":37,"area":"agents"},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2306.05167","title":"Decision S4: Efficient Sequence-Based RL via State Spaces Layers","created":"2023-06-08","cited_by_count":26,"area":"offlinerl"},{"id":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2509.20021","title":"Embodied AI: From LLMs to World Models","created":"2025-09-24","cited_by_count":24,"area":"wm"},{"id":"2302.07515","title":"TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play","created":"2023-02-15","cited_by_count":20,"area":null},{"id":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","cited_by_count":20,"area":"offlinerl"},{"id":"2306.13945","title":"Large Sequence Models for Sequential Decision-Making: A Survey","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2405.17272","title":"DPN: Decoupling Partition and Navigation for Neural Solvers of Min-max Vehicle Routing Problems","created":"2024-05-27","cited_by_count":18,"area":null},{"id":"2405.15821","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition","created":"2024-05-23","cited_by_count":16,"area":"agents"},{"id":"2211.03074","title":"A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization","created":"2022-11-06","cited_by_count":15,"area":null},{"id":"2212.07740","title":"Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformer","created":"2022-12-15","cited_by_count":14,"area":null},{"id":"2504.21048","title":"Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Survey","created":"2025-04-29","cited_by_count":14,"area":null},{"id":"2509.22698","title":"Advancing Audio-Visual Navigation Through Multi-Agent Collaboration in 3D Environments","created":"2025-09-21","cited_by_count":14,"area":null},{"id":"2407.08164","title":"Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks","created":"2024-07-11","cited_by_count":13,"area":null},{"id":"2411.01796","title":"Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge","created":"2024-11-04","cited_by_count":13,"area":null},{"id":"2508.14893","title":"Virtual Community: An Open World for Humans, Robots, and Society","created":"2025-08-20","cited_by_count":13,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2402.06700","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","created":"2024-02-09","cited_by_count":12,"area":"agents"},{"id":"2305.13937","title":"Multi-agent Continual Coordination via Progressive Task Contextualization","created":"2023-05-07","cited_by_count":11,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2311.02194","title":"AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation","created":"2023-11-03","cited_by_count":10,"area":"offlinerl"},{"id":"2402.08078","title":"Large Language Models as Agents in Two-Player Games","created":"2024-02-12","cited_by_count":10,"area":"agents"},{"id":"2410.01706","title":"Sable: a Performant, Efficient and Scalable Sequence Model for MARL","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2502.03723","title":"Speaking the Language of Teamwork: LLM-Guided Credit Assignment in Multi-Agent Reinforcement Learning","created":"2025-02-06","cited_by_count":10,"area":"agents"},{"id":"2511.05005","title":"Multi-agent Coordination via Flow Matching","created":"2025-11-07","cited_by_count":10,"area":"diffusion"},{"id":"2306.11551","title":"IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2402.04971","title":"Multi-Sender Persuasion: A Computational Perspective","created":"2024-02-07","cited_by_count":9,"area":null},{"id":"2212.12669","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","created":"2022-12-24","cited_by_count":8,"area":null},{"id":"2503.21200","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","created":"2025-03-27","cited_by_count":8,"area":null},{"id":"2508.06269","title":"OM2P: Offline Multi-Agent Mean-Flow Policy","created":"2025-08-08","cited_by_count":8,"area":"offlinerl"},{"id":"2211.08016","title":"Contextual Transformer for Offline Meta Reinforcement Learning","created":"2022-11-15","cited_by_count":7,"area":"offlinerl"},{"id":"2405.17152","title":"CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2509.22963","title":"Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces","created":"2025-09-26","cited_by_count":7,"area":"diffusion"},{"id":"2510.26389","title":"Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2607.13591","title":"Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents","created":"2026-07-15","cited_by_count":7,"area":"agents"},{"id":"2301.01919","title":"Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanism","created":"2023-01-05","cited_by_count":6,"area":null},{"id":"2302.04094","title":"Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation","created":"2023-02-08","cited_by_count":6,"area":null},{"id":"2306.02006","title":"MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement Learning","created":"2023-06-03","cited_by_count":6,"area":null},{"id":"2404.03869","title":"Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration","created":"2024-04-05","cited_by_count":6,"area":null},{"id":"2407.01548","title":"From Cognition to Computation: A Comparative Review of Human Attention and Transformer Architectures","created":"2024-04-25","cited_by_count":6,"area":null},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2410.16411","title":"The Duality of Generative AI and Reinforcement Learning in Robotics: A Review","created":"2024-10-21","cited_by_count":6,"area":"deeprl"},{"id":"2310.00871","title":"COMPOSER: Scalable and Robust Modular Policies for Snake Robots","created":"2023-10-02","cited_by_count":5,"area":null},{"id":"2310.05205","title":"GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2401.08728","title":"AgentMixer: Multi-Agent Correlated Policy Factorization","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2408.05686","title":"The Bandit Whisperer: Communication Learning for Restless Bandits","created":"2024-08-11","cited_by_count":5,"area":null},{"id":"2410.13953","title":"On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow","created":"2024-10-17","cited_by_count":5,"area":"diffusion"},{"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":"2504.03353","title":"Decentralized Collective World Model for Emergent Communication and Coordination","created":"2025-04-04","cited_by_count":5,"area":"wm"},{"id":"2605.07069","title":"Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems","created":"2026-05-08","cited_by_count":5,"area":"agents"},{"id":"2303.09032","title":"Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning","created":"2023-03-16","cited_by_count":4,"area":null},{"id":"2312.08466","title":"Efficiently Quantifying Individual Agent Importance in Cooperative MARL","created":"2023-12-13","cited_by_count":4,"area":null},{"id":"2401.13460","title":"Multi-Agent Diagnostics for Robustness via Illuminated Diversity","created":"2024-01-24","cited_by_count":4,"area":null},{"id":"2404.04205","title":"Enhancing IoT Intelligence: A Transformer-based Reinforcement Learning Methodology","created":"2024-04-05","cited_by_count":4,"area":"deeprl"},{"id":"2407.18414","title":"Adversarially Robust Decision Transformer","created":"2024-07-25","cited_by_count":4,"area":"offlinerl"},{"id":"2409.12001","title":"Putting Data at the Centre of Offline Multi-Agent Reinforcement Learning","created":"2024-09-18","cited_by_count":4,"area":"offlinerl"},{"id":"2502.01932","title":"VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play","created":"2025-02-04","cited_by_count":4,"area":"deeprl"},{"id":"2505.05968","title":"Offline Multi-agent Reinforcement Learning via Sequential Score Decomposition","created":"2025-05-09","cited_by_count":4,"area":"offlinerl"},{"id":"2506.18348","title":"Dynamic Knowledge Exchange and Dual-diversity Review: Concisely Unleashing the Potential of a Multi-Agent Research Team","created":"2025-06-23","cited_by_count":4,"area":"agents"},{"id":"2506.24019","title":"Ella: Embodied Social Agents with Lifelong Memory","created":"2025-06-30","cited_by_count":4,"area":"agents"},{"id":"2305.13936","title":"Robust Multi-agent Communication via Multi-view Message Certification","created":"2023-05-07","cited_by_count":3,"area":null},{"id":"2310.11846","title":"MaskMA: Towards Zero-Shot Multi-Agent Decision Making with Mask-Based Collaborative Learning","created":"2023-10-18","cited_by_count":3,"area":null},{"id":"2406.02890","title":"Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2505.05262","title":"Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2507.18059","title":"Multi-Agent Guided Policy Optimization","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2508.06836","title":"Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learning","created":"2025-08-09","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":"2602.17062","title":"Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2302.09605","title":"Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning","created":"2023-02-19","cited_by_count":2,"area":"offlinerl"},{"id":"2310.04796","title":"Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2312.16189","title":"OpenRL: A Unified Reinforcement Learning Framework","created":"2023-12-20","cited_by_count":2,"area":null},{"id":"2402.00972","title":"Closure Discovery for Coarse-Grained Partial Differential Equations Using Grid-based Reinforcement Learning","created":"2024-02-01","cited_by_count":2,"area":"deeprl"},{"id":"2402.14090","title":"Social Environment Design","created":"2024-02-21","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":"2407.12505","title":"Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments","created":"2024-07-17","cited_by_count":2,"area":"deeprl"},{"id":"2408.06087","title":"Building Decision Making Models Through Language Model Regime","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2410.19382","title":"Multi-Agent Reinforcement Learning with Selective State-Space Models","created":"2024-10-25","cited_by_count":2,"area":"ssm"},{"id":"2502.10148","title":"Closed-Loop Vision-Language Planning for Multi-Agent Coordination","created":"2025-02-14","cited_by_count":2,"area":"agents"},{"id":"2503.11726","title":"SPECTra: Scalable Multi-Agent Reinforcement Learning with Permutation-Free Networks","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2508.18514","title":"Breaking Through Barren Plateaus: Reinforcement Learning Initializations for Deep Variational Quantum Circuits","created":"2025-08-25","cited_by_count":2,"area":"deeprl"},{"id":"2508.20315","title":"Multi-Agent Reinforcement Learning in Intelligent Transportation Systems: A Comprehensive Survey","created":"2025-08-27","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":"2602.17009","title":"Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2604.13472","title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2305.07182","title":"Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learning","created":"2023-05-12","cited_by_count":1,"area":null},{"id":"2305.07856","title":"Stackelberg Decision Transformer for Asynchronous Action Coordination in Multi-Agent Systems","created":"2023-05-13","cited_by_count":1,"area":"offlinerl"},{"id":"2310.05053","title":"FP3O: Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility","created":"2023-10-08","cited_by_count":1,"area":null},{"id":"2403.15916","title":"Multi-agent transformer-accelerated RL for satisfaction of STL specifications","created":"2024-03-23","cited_by_count":1,"area":null},{"id":"2404.11144","title":"Self-adaptive PSRO: Towards an Automatic Population-based Game Solver","created":"2024-04-17","cited_by_count":1,"area":null}],"next_cursor":"100"}