{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/multi-agent-reinforcement-learning/papers/7","list_of":"/task/multi-agent-reinforcement-learning","task":"Multi-agent Reinforcement Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":7,"pages_in_order":18,"rows_per_page":100,"rows":[601,700],"of":1718,"counts":{"archive_papers_tagged":1718,"with_a_code_link":522,"where_syntology_ran_a_sample":135,"not_listed_spam_title":0,"listed":1718,"listed_where_code_ran":135,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":119,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":119,"listed_every_run_a_failure_of_syntologys_instrument":16,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/multi-agent-reinforcement-learning","prev":"/task/multi-agent-reinforcement-learning/papers/6","next":"/task/multi-agent-reinforcement-learning/papers/8","papers":[{"url":null,"slug":"iterative-multi-agent-reinforcement-learning","title":"Iterative Multi-Agent Reinforcement Learning: A Novel Approach Toward Real-World Multi-Echelon Inventory Optimization","date":"2025-03-23","arxiv_id":"2503.18201","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-roadmap-towards-improving-multi-agent","title":"A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And Inference","date":"2025-03-22","arxiv_id":"2503.17803","repositories_listed":0,"syntology":null},{"url":null,"slug":"penguin-partially-equivariant-graph-neural","title":"PEnGUiN: Partially Equivariant Graph NeUral Networks for Sample Efficient MARL","date":"2025-03-19","arxiv_id":"2503.15615","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-multi-agent-specialization-via","title":"Predicting Multi-Agent Specialization via Task Parallelizability","date":"2025-03-19","arxiv_id":"2503.15703","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-on-multi-agent","title":"A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives","date":"2025-03-17","arxiv_id":"2503.13415","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-better-sample-efficiency-in-multi","title":"Towards Better Sample Efficiency in Multi-Agent Reinforcement Learning via Exploration","date":"2025-03-17","arxiv_id":"2503.13077","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-mediated-guidance-of-marl-systems","title":"LLM-Mediated Guidance of MARL Systems","date":"2025-03-16","arxiv_id":"2503.13553","repositories_listed":0,"syntology":null},{"url":null,"slug":"icco-learning-an-instruction-conditioned","title":"ICCO: Learning an Instruction-conditioned Coordinator for Language-guided Task-aligned Multi-robot Control","date":"2025-03-15","arxiv_id":"2503.12122","repositories_listed":0,"syntology":null},{"url":null,"slug":"unicorn-a-universal-and-collaborative","title":"Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Control","date":"2025-03-14","arxiv_id":"2503.11488","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-multi-agent-systems-via","title":"Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy","date":"2025-03-13","arxiv_id":"2503.10049","repositories_listed":0,"syntology":null},{"url":null,"slug":"h2-marl-multi-agent-reinforcement-learning","title":"H2-MARL: Multi-Agent Reinforcement Learning for Pareto Optimality in Hospital Capacity Strain and Human Mobility during Epidemic","date":"2025-03-13","arxiv_id":"2503.10907","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributionally-robust-multi-agent","title":"Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping","date":"2025-03-12","arxiv_id":"2503.09755","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-traffic-signal-control-through","title":"Enhancing Traffic Signal Control through Model-based Reinforcement Learning and Policy Reuse","date":"2025-03-11","arxiv_id":"2503.08728","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-marl-a-quantum-inspired-algorithm-using","title":"Q-MARL: A quantum-inspired algorithm using neural message passing for large-scale multi-agent reinforcement learning","date":"2025-03-10","arxiv_id":"2503.07397","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-a-single-actor-to-output-personalized","title":"Using a single actor to output personalized policy for different intersections","date":"2025-03-10","arxiv_id":"2503.07678","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-decentralized-maddpg-with-networked","title":"Fully-Decentralized MADDPG with Networked Agents","date":"2025-03-09","arxiv_id":"2503.06747","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-robot-collaboration-through","title":"Multi-Robot Collaboration through Reinforcement Learning and Abstract Simulation","date":"2025-03-07","arxiv_id":"2503.05092","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-implicit-preference-based-policy-fine","title":"Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm","date":"2025-03-05","arxiv_id":"2503.03796","repositories_listed":0,"syntology":null},{"url":null,"slug":"pretrained-llms-as-real-time-controllers-for","title":"Pretrained LLMs as Real-Time Controllers for Robot Operated Serial Production Line","date":"2025-03-05","arxiv_id":"2503.03889","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-reinforcement-learning-for-1","title":"Decentralized Reinforcement Learning for Multi-Agent Multi-Resource Allocation via Dynamic Cluster Agreements","date":"2025-03-04","arxiv_id":"2503.02437","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01069","title":"Multi-Agent Reinforcement Learning with Long-Term Performance Objectives for Service Workforce Optimization","date":"2025-03-03","arxiv_id":"2503.01069","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01458","title":"SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning","date":"2025-03-03","arxiv_id":"2503.01458","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-m-3-text-hf-multi-agent-reinforcement","title":"M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality","date":"2025-03-03","arxiv_id":"2503.02077","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-00684","title":"Factorized Deep Q-Network for Cooperative Multi-Agent Reinforcement Learning in Victim Tagging","date":"2025-03-02","arxiv_id":"2503.00684","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-00372","title":"Nucleolus Credit Assignment for Effective Coalitions in Multi-agent Reinforcement Learning","date":"2025-03-01","arxiv_id":"2503.00372","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generative-model-enhanced-multi-agent","title":"A Generative Model Enhanced Multi-Agent Reinforcement Learning Method for Electric Vehicle Charging Navigation","date":"2025-02-27","arxiv_id":"2502.20068","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-multi-agent-assignment-over","title":"Cooperative Multi-Agent Assignment over Stochastic Graphs via Constrained Reinforcement Learning","date":"2025-02-27","arxiv_id":"2502.20462","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-large-language-models-for-26","title":"Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignment","date":"2025-02-24","arxiv_id":"2502.16863","repositories_listed":0,"syntology":null},{"url":null,"slug":"facilitating-emergency-vehicle-passage-in","title":"Facilitating Emergency Vehicle Passage in Congested Urban Areas Using Multi-agent Deep Reinforcement Learning","date":"2025-02-23","arxiv_id":"2502.16449","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-dependency-dynamics-in-multi-agent","title":"Toward Dependency Dynamics in Multi-Agent Reinforcement Learning for Traffic Signal Control","date":"2025-02-23","arxiv_id":"2502.16608","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-mean-field-multi-agent-reinforcement","title":"Causal Mean Field Multi-Agent Reinforcement Learning","date":"2025-02-20","arxiv_id":"2502.14200","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-based-generic-potential-function-for","title":"Vision-Based Generic Potential Function for Policy Alignment in Multi-Agent Reinforcement Learning","date":"2025-02-19","arxiv_id":"2502.13430","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-vehicles-using-multi-agent","title":"Collaboration Between the City and Machine Learning Community is Crucial to Efficient Autonomous Vehicles Routing","date":"2025-02-18","arxiv_id":"2502.13188","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypernetwork-based-approach-for-optimal","title":"Hypernetwork-based approach for optimal composition design in partially controlled multi-agent systems","date":"2025-02-18","arxiv_id":"2502.12605","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-multi-agent-planning-with","title":"Cooperative Multi-Agent Planning with Adaptive Skill Synthesis","date":"2025-02-14","arxiv_id":"2502.10148","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-is-more-task-efficient-skill-discovery","title":"Few is More: Task-Efficient Skill-Discovery for Multi-Task Offline Multi-Agent Reinforcement Learning","date":"2025-02-13","arxiv_id":"2502.08985","repositories_listed":0,"syntology":null},{"url":null,"slug":"incentivize-without-bonus-provably-efficient","title":"Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games","date":"2025-02-13","arxiv_id":"2502.09780","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-marl-a-graph-based-solution-for-large-scale","title":"Q-MARL: A GRAPH-BASED SOLUTION FOR LARGE-SCALE MULTI-AGENT REINFORCEMENT LEARNING INSPIRED BY QUANTUM CHEMISTRY","date":"2025-02-13","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"centrally-coordinated-multi-agent","title":"Centrally Coordinated Multi-Agent Reinforcement Learning for Power Grid Topology Control","date":"2025-02-12","arxiv_id":"2502.08681","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-ai-enhanced-cooperative-mec-of","title":"Generative AI-Enhanced Cooperative MEC of UAVs and Ground Stations for Unmanned Surface Vehicles","date":"2025-02-12","arxiv_id":"2502.08119","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-value-decomposition-networks-with","title":"Distributed Value Decomposition Networks with Networked Agents","date":"2025-02-11","arxiv_id":"2502.07635","repositories_listed":0,"syntology":null},{"url":null,"slug":"who-is-helping-whom-analyzing-inter","title":"Who is Helping Whom? Analyzing Inter-dependencies to Evaluate Cooperation in Human-AI Teaming","date":"2025-02-10","arxiv_id":"2502.06976","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-powered-decentralized-generative-agents","title":"LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning","date":"2025-02-08","arxiv_id":"2502.05453","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-agent-specific-adaptation-lorasa-for","title":"Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning","date":"2025-02-08","arxiv_id":"2502.05573","repositories_listed":0,"syntology":null},{"url":null,"slug":"tar-2-temporal-agent-reward-redistribution","title":"$TAR^2$: Temporal-Agent Reward Redistribution for Optimal Policy Preservation in Multi-Agent Reinforcement Learning","date":"2025-02-07","arxiv_id":"2502.04864","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-location-planning-for-ai-defined","title":"Online Location Planning for AI-Defined Vehicles: Optimizing Joint Tasks of Order Serving and Spatio-Temporal Heterogeneous Model Fine-Tuning","date":"2025-02-06","arxiv_id":"2502.04399","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-on-aya-dyads-to","title":"Reinforcement Learning on Dyads to Enhance Medication Adherence","date":"2025-02-06","arxiv_id":"2502.06835","repositories_listed":0,"syntology":null},{"url":null,"slug":"simulating-the-emergence-of-differential-case","title":"Simulating the Emergence of Differential Case Marking with Communicating Neural-Network Agents","date":"2025-02-06","arxiv_id":"2502.04038","repositories_listed":0,"syntology":null},{"url":null,"slug":"double-distillation-network-for-multi-agent","title":"Double Distillation Network for Multi-Agent Reinforcement Learning","date":"2025-02-05","arxiv_id":"2502.03125","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-efficient-flying-lora-gateways-a-multi","title":"Energy-Efficient Flying LoRa Gateways: A Multi-Agent Reinforcement Learning Approach","date":"2025-02-05","arxiv_id":"2502.03377","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-efficient-flocking-control-based-on","title":"Learning Efficient Flocking Control based on Gibbs Random Fields","date":"2025-02-05","arxiv_id":"2502.02984","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimistic-e-greedy-exploration-for","title":"Optimistic ε-Greedy Exploration for Cooperative Multi-Agent Reinforcement Learning","date":"2025-02-05","arxiv_id":"2502.03506","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-multi-objective-multi-agent","title":"Sequential Multi-objective Multi-agent Reinforcement Learning Approach for Predictive Maintenance","date":"2025-02-04","arxiv_id":"2502.02071","repositories_listed":0,"syntology":null},{"url":null,"slug":"volleybots-a-testbed-for-multi-drone","title":"VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play","date":"2025-02-04","arxiv_id":"2502.01932","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-theory-of-mind-enables-the-invention","title":"Visual Theory of Mind Enables the Invention of Proto-Writing","date":"2025-02-03","arxiv_id":"2502.01568","repositories_listed":0,"syntology":null},{"url":null,"slug":"b3c-a-minimalist-approach-to-offline-multi","title":"B3C: A Minimalist Approach to Offline Multi-Agent Reinforcement Learning","date":"2025-01-30","arxiv_id":"2501.18138","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-mean-field-control-on-sparse-graphs","title":"Learning Mean Field Control on Sparse Graphs","date":"2025-01-28","arxiv_id":"2501.17079","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-ai-based-decentralized-resource","title":"Adaptive AI-based Decentralized Resource Management in the Cloud-Edge Continuum","date":"2025-01-27","arxiv_id":"2501.15802","repositories_listed":0,"syntology":null},{"url":null,"slug":"selective-experience-sharing-in-reinforcement","title":"Selective Experience Sharing in Reinforcement Learning Enhances Interference Management","date":"2025-01-27","arxiv_id":"2501.15735","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-knowledge-sharing-in-multi-agent","title":"Contextual Knowledge Sharing in Multi-Agent Reinforcement Learning with Decentralized Communication and Coordination","date":"2025-01-26","arxiv_id":"2501.15695","repositories_listed":0,"syntology":null},{"url":null,"slug":"bmg-q-localized-bipartite-match-graph","title":"BMG-Q: Localized Bipartite Match Graph Attention Q-Learning for Ride-Pooling Order Dispatch","date":"2025-01-23","arxiv_id":"2501.13448","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-offline-multi-agent-reinforcement-learning","title":"An Offline Multi-Agent Reinforcement Learning Framework for Radio Resource Management","date":"2025-01-22","arxiv_id":"2501.12991","repositories_listed":0,"syntology":null},{"url":null,"slug":"experience-replay-innovative-dynamics","title":"Experience-replay Innovative Dynamics","date":"2025-01-21","arxiv_id":"2501.12199","repositories_listed":0,"syntology":null},{"url":null,"slug":"adage-a-generic-two-layer-framework-for","title":"ADAGE: A generic two-layer framework for adaptive agent based modelling","date":"2025-01-16","arxiv_id":"2501.09429","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-to-quiet","title":"A Reinforcement Learning Approach to Quiet and Safe UAM Traffic Management","date":"2025-01-15","arxiv_id":"2501.08941","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoresttest-a-tool-for-automated-rest-api","title":"AutoRestTest: A Tool for Automated REST API Testing Using LLMs and MARL","date":"2025-01-15","arxiv_id":"2501.08600","repositories_listed":0,"syntology":null},{"url":null,"slug":"networked-agents-in-the-dark-team-value","title":"Networked Agents in the Dark: Team Value Learning under Partial Observability","date":"2025-01-15","arxiv_id":"2501.08778","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-pricing-in-high-speed-railways-using","title":"Dynamic Pricing in High-Speed Railways Using Multi-Agent Reinforcement Learning","date":"2025-01-14","arxiv_id":"2501.08234","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-enhancing-sensing","title":"Reinforcement Learning for Enhancing Sensing Estimation in Bistatic ISAC Systems with UAV Swarms","date":"2025-01-11","arxiv_id":"2501.06454","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-optimization-of-charged-particle","title":"Constrained Optimization of Charged Particle Tracking with Multi-Agent Reinforcement Learning","date":"2025-01-09","arxiv_id":"2501.05113","repositories_listed":0,"syntology":null},{"url":null,"slug":"turn-based-multi-agent-reinforcement-learning","title":"Turn-based Multi-Agent Reinforcement Learning Model Checking","date":"2025-01-06","arxiv_id":"2501.03187","repositories_listed":0,"syntology":null},{"url":null,"slug":"cord-generalizable-cooperation-via-role","title":"CORD: Generalizable Cooperation via Role Diversity","date":"2025-01-04","arxiv_id":"2501.02221","repositories_listed":0,"syntology":null},{"url":null,"slug":"pimaex-multi-agent-exploration-through-peer","title":"PIMAEX: Multi-Agent Exploration through Peer Incentivization","date":"2025-01-02","arxiv_id":"2501.01266","repositories_listed":0,"syntology":null},{"url":null,"slug":"symmetries-enhanced-multi-agent-reinforcement","title":"Symmetries-enhanced Multi-Agent Reinforcement Learning","date":"2025-01-02","arxiv_id":"2501.01136","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-traffic-control-in-complex","title":"Distributed Traffic Control in Complex Dynamic Roadblocks: A Multi-Agent Deep RL Approach","date":"2024-12-31","arxiv_id":"2501.00211","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-emergent-communication-large","title":"Generative Emergent Communication: Large Language Model is a Collective World Model","date":"2024-12-31","arxiv_id":"2501.00226","repositories_listed":0,"syntology":null},{"url":null,"slug":"game-theory-and-multi-agent-reinforcement","title":"Game Theory and Multi-Agent Reinforcement Learning : From Nash Equilibria to Evolutionary Dynamics","date":"2024-12-29","arxiv_id":"2412.20523","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-hierarchical-reinforcement-learning","title":"Scalable Hierarchical Reinforcement Learning for Hyper Scale Multi-Robot Task Planning","date":"2024-12-27","arxiv_id":"2412.19538","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-multi-agent-meta-reinforcement","title":"Hierarchical Multi-agent Meta-Reinforcement Learning for Cross-channel Bidding","date":"2024-12-26","arxiv_id":"2412.19064","repositories_listed":0,"syntology":null},{"url":null,"slug":"tacit-learning-with-adaptive-information","title":"Tacit Learning with Adaptive Information Selection for Cooperative Multi-Agent Reinforcement Learning","date":"2024-12-20","arxiv_id":"2412.15639","repositories_listed":0,"syntology":null},{"url":null,"slug":"agent-temporal-credit-assignment-for-optimal","title":"Agent-Temporal Credit Assignment for Optimal Policy Preservation in Sparse Multi-Agent Reinforcement Learning","date":"2024-12-19","arxiv_id":"2412.14779","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-diversity-is-key-to-collective","title":"The impact of behavioral diversity in multi-agent reinforcement learning","date":"2024-12-19","arxiv_id":"2412.16244","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-multi-agent-reinforcement-3","title":"Heterogeneous Multi-Agent Reinforcement Learning for Distributed Channel Access in WLANs","date":"2024-12-18","arxiv_id":"2412.14218","repositories_listed":0,"syntology":null},{"url":null,"slug":"coordinated-power-smoothing-control-for-wind","title":"Coordinated Power Smoothing Control for Wind Storage Integrated System with Physics-informed Deep Reinforcement Learning","date":"2024-12-17","arxiv_id":"2412.17838","repositories_listed":0,"syntology":null},{"url":null,"slug":"achieving-collective-welfare-in-multi-agent","title":"Achieving Collective Welfare in Multi-Agent Reinforcement Learning via Suggestion Sharing","date":"2024-12-16","arxiv_id":"2412.12326","repositories_listed":0,"syntology":null},{"url":null,"slug":"cluster-based-multi-agent-task-scheduling-for","title":"Cluster-Based Multi-Agent Task Scheduling for Space-Air-Ground Integrated Networks","date":"2024-12-14","arxiv_id":"2412.10700","repositories_listed":0,"syntology":null},{"url":null,"slug":"gtde-grouped-training-with-decentralized","title":"GTDE: Grouped Training with Decentralized Execution for Multi-agent Actor-Critic","date":"2024-12-12","arxiv_id":"2501.10367","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-train-based-distributed-multi-agent","title":"Quantum-Train-Based Distributed Multi-Agent Reinforcement Learning","date":"2024-12-12","arxiv_id":"2412.08845","repositories_listed":0,"syntology":null},{"url":null,"slug":"steganography-in-game-actions","title":"Steganography in Game Actions","date":"2024-12-11","arxiv_id":"2412.10442","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-multi-agent-reinforcement-learning-2","title":"Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization","date":"2024-12-10","arxiv_id":"2412.07639","repositories_listed":0,"syntology":null},{"url":null,"slug":"intersection-aware-assessment-of-ems","title":"Intersection-Aware Assessment of EMS Accessibility in NYC: A Data-Driven Approach","date":"2024-12-05","arxiv_id":"2412.04369","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-freeway-lane","title":"Reinforcement Learning for Freeway Lane-Change Regulation via Connected Vehicles","date":"2024-12-05","arxiv_id":"2412.04341","repositories_listed":0,"syntology":null},{"url":null,"slug":"traffic-co-simulation-framework-empowered-by","title":"Traffic Co-Simulation Framework Empowered by Infrastructure Camera Sensing and Reinforcement Learning","date":"2024-12-05","arxiv_id":"2412.03925","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-analysis-of-multi-agent","title":"Comparative Analysis of Multi-Agent Reinforcement Learning Policies for Crop Planning Decision Support","date":"2024-12-03","arxiv_id":"2412.02057","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-problem-of-social-cost-in-multi-agent","title":"The Problem of Social Cost in Multi-Agent General Reinforcement Learning: Survey and Synthesis","date":"2024-12-03","arxiv_id":"2412.02091","repositories_listed":0,"syntology":null},{"url":null,"slug":"mean-field-sampling-for-cooperative-multi","title":"Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning","date":"2024-12-01","arxiv_id":"2412.00661","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-local-information-aggregation-based-multi","title":"A Local Information Aggregation based Multi-Agent Reinforcement Learning for Robot Swarm Dynamic Task Allocation","date":"2024-11-29","arxiv_id":"2411.19526","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-transit-signal-priority-into","title":"Integrating Transit Signal Priority into Multi-Agent Reinforcement Learning based Traffic Signal Control","date":"2024-11-28","arxiv_id":"2411.19359","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-multi-agent-reinforcement-learning-with-2","title":"Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibrium","date":"2024-11-22","arxiv_id":"2411.15036","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-strategy","title":"Multi-agent reinforcement learning strategy to maximize the lifetime of Wireless Rechargeable","date":"2024-11-21","arxiv_id":"2411.14496","repositories_listed":0,"syntology":null}],"record_sha256":"a154b0f21567f700a89db8b322e94cb506b9b5048b86ef12c701d3d55ec62f0c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}