{"total":98,"rows":[{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2405.08550","title":"Learning Multi-Agent Communication from Graph Modeling Perspective","created":"2024-05-14","cited_by_count":48,"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":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"area":null},{"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":"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":"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":"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":"2410.01706","title":"Sable: a Performant, Efficient and Scalable Sequence Model for MARL","created":"2024-10-02","cited_by_count":10,"area":null},{"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":"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":"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":"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":"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":"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":"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":"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":"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":"2402.14090","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":"2408.06087","title":"Building Decision Making Models Through Language Model Regime","created":"2024-08-12","cited_by_count":2,"area":null},{"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":"2508.20315","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":"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},{"id":"2408.11564","title":"AutoDirector: Online Auto-scheduling Agents for Multi-sensory Composition","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2502.16496","title":"PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2508.02826","title":"TransAM: Transformer-Based Agent Modeling for Multi-Agent Systems via Local Trajectory Encoding","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2510.13343","title":"AOAD-MAT: Transformer-based multi-agent deep reinforcement learning model considering agents' order of action decisions","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2511.17435","title":"Multi-Agent Pointer Transformer: Seq-to-Seq Reinforcement Learning for Multi-Vehicle Dynamic Pickup-Delivery Problems","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2312.02522","title":"MASP: Scalable GNN-based Planning for Multi-Agent Navigation","created":"2023-12-05","cited_by_count":0,"area":null},{"id":"2403.18057","title":"Prioritized League Reinforcement Learning for Large-Scale Heterogeneous Multiagent Systems","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2408.07395","title":"Improving Global Parameter-sharing in Physically Heterogeneous Multi-agent Reinforcement Learning with Unified Action Space","created":"2024-08-14","cited_by_count":0,"area":null},{"id":"2409.07127","title":"DCMAC: Demand-aware Customized Multi-Agent Communication via Upper Bound Training","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2410.01575","title":"Computing Ex Ante Equilibrium in Heterogeneous Zero-Sum Team Games","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2410.06372","title":"Cooperative and Asynchronous Transformer-based Mission Planning for Heterogeneous Teams of Mobile Robots","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2411.00382","title":"Communication Learning in Multi-Agent Systems from Graph Modeling Perspective","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2412.03072","title":"Preference-based opponent shaping in differentiable games","created":"2024-12-04","cited_by_count":0,"area":null},{"id":"2507.14553","title":"Clutter Detection and Removal by Multi-Objective Analysis for Photographic Guidance","created":"2025-07-19","cited_by_count":0,"area":null},{"id":"2507.22782","title":"Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2508.13661","title":"Communication-Enhanced Tutoring for Efficient Decentralized Multi-Agent Reinforcement Learning","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2509.23778","title":"Sequence Pathfinder for Multi-Agent Pickup and Delivery in the Warehouse","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2511.21934","title":"Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2602.02903","title":"Spatiotemporal Decision Transformer for Traffic Coordination","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.19223","title":"Characterizing MARL for Energy Control: A Multi-KPI Benchmark on the CityLearn Environment","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2602.21680","title":"Hierarchical Lead Critic based Multi-Agent Reinforcement Learning","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2605.14235","title":"Quantum Advantage in Multi Agent Reinforcement Learning","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.31023","title":"HADT: A Heterogeneous Multi-Agent Differential Transformer for Autonomous Earth Observation Satellite Cluster","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.25526","title":"Low Variance Trust Region Optimization with Independent Actors and Sequential Updates in Cooperative Multi-agent Reinforcement Learning","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.30072","title":"ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.03324","title":"Hierarchical Multi-Agent Reinforcement Learning for Carbon-Aware AI Data Centers in Power Distribution Systems","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.04972","title":"Multi-Robot Open Adaptive Teaming Across Unseen Environments, Partners, and Scales","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.09422","title":"Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.13418","title":"Can We Steer the Black-Box? Towards Controllability-Centric Evaluation of Recommender Systems with Collaborative Agents","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.17924","title":"Aggregate in the Advantage, Not the Ratio: A Canonical-Form Analysis of Cooperative Multi-Agent Policy Optimization","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.19548","title":"Modeling Fly Social Behavior with Agent-Centric Pose Forecasting","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.05340","title":"Multi-Agent Transformer for Queue-Level XR Traffic Scheduling in TSN Networks","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.07148","title":"A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturing","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.26683","title":"SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.06930","title":"Distributed Dexterous Manipulation with Spatially Conditioned Multi-Agent Transformers","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.31531","title":"HySTAR: Anchored Hypergraphs for Stable Credit Assignment in Cooperative Multi-Agent Reinforcement Learning","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.38889","title":"VERA: Verifiable Feasibility Representations with Counterfactual Credit for Constrained Multi-Agent Control","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02847","title":"Turnover-Orthogonal Credit Assignment for Open-Team Multi-Agent Reinforcement Learning","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}