{"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/10","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":10,"pages_in_order":18,"rows_per_page":100,"rows":[901,1000],"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/9","next":"/task/multi-agent-reinforcement-learning/papers/11","papers":[{"url":null,"slug":"how-much-can-change-in-a-year-revisiting","title":"How much can change in a year? Revisiting Evaluation in Multi-Agent Reinforcement Learning","date":"2023-12-13","arxiv_id":"2312.08463","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-diagnostics-for-understanding-agent","title":"On Diagnostics for Understanding Agent Training Behaviour in Cooperative MARL","date":"2023-12-13","arxiv_id":"2312.08468","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-distribution-decomposition-based-multi","title":"Noise Distribution Decomposition based Multi-Agent Distributional Reinforcement Learning","date":"2023-12-12","arxiv_id":"2312.07025","repositories_listed":0,"syntology":null},{"url":null,"slug":"dcir-dynamic-consistency-intrinsic-reward-for","title":"DCIR: Dynamic Consistency Intrinsic Reward for Multi-Agent Reinforcement Learning","date":"2023-12-10","arxiv_id":"2312.05783","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-multi-agent-reinforcement","title":"Privacy Preserving Multi-Agent Reinforcement Learning in Supply Chains","date":"2023-12-09","arxiv_id":"2312.05686","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-horizon-reinforcement-learning-in","title":"Finite Horizon Multi-Agent Reinforcement Learning in Solving Optimal Control of State-Dependent Switched Systems","date":"2023-12-08","arxiv_id":"2312.04767","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-scalable-network-aware-multi-agent","title":"A Scalable Network-Aware Multi-Agent Reinforcement Learning Framework for Decentralized Inverter-based Voltage Control","date":"2023-12-07","arxiv_id":"2312.04371","repositories_listed":0,"syntology":null},{"url":null,"slug":"macca-offline-multi-agent-reinforcement","title":"MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit Assignment","date":"2023-12-06","arxiv_id":"2312.03644","repositories_listed":0,"syntology":null},{"url":null,"slug":"extreme-event-prediction-with-multi-agent","title":"Extreme Event Prediction with Multi-agent Reinforcement Learning-based Parametrization of Atmospheric and Oceanic Turbulence","date":"2023-12-01","arxiv_id":"2312.00907","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalisable-agents-for-neural-network","title":"Generalisable Agents for Neural Network Optimisation","date":"2023-11-30","arxiv_id":"2311.18598","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimax-exploiter-a-data-efficient-approach","title":"Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play","date":"2023-11-28","arxiv_id":"2311.17190","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-for-power-1","title":"Multi-Agent Reinforcement Learning for Power Control in Wireless Networks via Adaptive Graphs","date":"2023-11-27","arxiv_id":"2311.15858","repositories_listed":0,"syntology":null},{"url":null,"slug":"directly-attention-loss-adjusted-prioritized","title":"Directly Attention Loss Adjusted Prioritized Experience Replay","date":"2023-11-24","arxiv_id":"2311.14390","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlling-large-language-model-based-agents","title":"Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach","date":"2023-11-23","arxiv_id":"2311.13884","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-user-pairing-and-beamforming-design-of","title":"Joint User Pairing and Beamforming Design of Multi-STAR-RISs-Aided NOMA in the Indoor Environment via Multi-Agent Reinforcement Learning","date":"2023-11-15","arxiv_id":"2311.08708","repositories_listed":0,"syntology":null},{"url":null,"slug":"untargeted-black-box-attacks-for-social","title":"Multi-agent Attacks for Black-box Social Recommendations","date":"2023-11-13","arxiv_id":"2311.07127","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-multi-agent-coordination-through","title":"Enhancing Multi-Agent Coordination through Common Operating Picture Integration","date":"2023-11-08","arxiv_id":"2311.04740","repositories_listed":0,"syntology":null},{"url":null,"slug":"social-motion-prediction-with-cognitive","title":"Social Motion Prediction with Cognitive Hierarchies","date":"2023-11-08","arxiv_id":"2311.04726","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-decentralized-traffic-signal","title":"Learning Decentralized Traffic Signal Controllers with Multi-Agent Graph Reinforcement Learning","date":"2023-11-07","arxiv_id":"2311.03756","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-enabled-unmanned-vehicle-assisted","title":"AI-Enabled Unmanned Vehicle-Assisted Reconfigurable Intelligent Surfaces: Deployment, Prototyping, Experiments, and Opportunities","date":"2023-11-06","arxiv_id":"2311.04241","repositories_listed":0,"syntology":null},{"url":null,"slug":"environmental-impact-based-multi-agent","title":"Environmental-Impact Based Multi-Agent Reinforcement Learning","date":"2023-11-06","arxiv_id":"2311.04240","repositories_listed":0,"syntology":null},{"url":null,"slug":"kindness-in-multi-agent-reinforcement","title":"Kindness in Multi-Agent Reinforcement Learning","date":"2023-11-06","arxiv_id":"2311.04239","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-independently-from-causality-in","title":"Learning Independently from Causality in Multi-Agent Environments","date":"2023-11-05","arxiv_id":"2311.02741","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-agent-reinforcement-learning-1","title":"A Multi-Agent Reinforcement Learning Framework for Evaluating the U.S. Ending the HIV Epidemic Plan","date":"2023-11-01","arxiv_id":"2311.00855","repositories_listed":0,"syntology":null},{"url":null,"slug":"qfree-a-universal-value-function","title":"QFree: A Universal Value Function Factorization for Multi-Agent Reinforcement Learning","date":"2023-11-01","arxiv_id":"2311.00356","repositories_listed":0,"syntology":null},{"url":null,"slug":"fair-collaborative-vehicle-routing-a-deep","title":"Fair collaborative vehicle routing: A deep multi-agent reinforcement learning approach","date":"2023-10-26","arxiv_id":"2310.17485","repositories_listed":0,"syntology":null},{"url":null,"slug":"goals-are-enough-inducing-adhoc-cooperation","title":"Goals are Enough: Inducing AdHoc cooperation among unseen Multi-Agent systems in IMFs","date":"2023-10-26","arxiv_id":"2310.17416","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-agent-as-urban-planner-steering","title":"AI Agent as Urban Planner: Steering Stakeholder Dynamics in Urban Planning via Consensus-based Multi-Agent Reinforcement Learning","date":"2023-10-25","arxiv_id":"2310.16772","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiprompter-cooperative-prompt-optimization","title":"MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning","date":"2023-10-25","arxiv_id":"2310.16730","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-conventions-for-human-ai","title":"Diverse Conventions for Human-AI Collaboration","date":"2023-10-24","arxiv_id":"2310.15414","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-zero-shot-learning-in-restless-multi","title":"Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization","date":"2023-10-23","arxiv_id":"2310.14526","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-resource-management-in-integrated","title":"Dynamic Resource Management in Integrated NOMA Terrestrial-Satellite Networks using Multi-Agent Reinforcement Learning","date":"2023-10-18","arxiv_id":"2310.11814","repositories_listed":0,"syntology":null},{"url":null,"slug":"fact-based-agent-modeling-for-multi-agent","title":"Fact-based Agent modeling for Multi-Agent Reinforcement Learning","date":"2023-10-18","arxiv_id":"2310.12290","repositories_listed":0,"syntology":null},{"url":null,"slug":"marvel-multi-agent-reinforcement-learning-for","title":"MARVEL: Multi-Agent Reinforcement-Learning for Large-Scale Variable Speed Limits","date":"2023-10-18","arxiv_id":"2310.12359","repositories_listed":0,"syntology":null},{"url":null,"slug":"combat-urban-congestion-via-collaboration","title":"Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control","date":"2023-10-17","arxiv_id":"2310.10948","repositories_listed":0,"syntology":null},{"url":null,"slug":"mir2-towards-provably-robust-multi-agent","title":"Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization","date":"2023-10-15","arxiv_id":"2310.09833","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustness-to-multi-modal-environment","title":"Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning","date":"2023-10-12","arxiv_id":"2310.08746","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-agent-interaction-in-multi-agent","title":"Quantifying Agent Interaction in Multi-agent Reinforcement Learning for Cost-efficient Generalization","date":"2023-10-11","arxiv_id":"2310.07218","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-multi-agent-rl-an","title":"Sample-Efficient Multi-Agent RL: An Optimization Perspective","date":"2023-10-10","arxiv_id":"2310.06243","repositories_listed":0,"syntology":null},{"url":null,"slug":"replication-of-multi-agent-reinforcement","title":"Replication of Multi-agent Reinforcement Learning for the \"Hide and Seek\" Problem","date":"2023-10-09","arxiv_id":"2310.05430","repositories_listed":0,"syntology":null},{"url":null,"slug":"fp3o-enabling-proximal-policy-optimization-in","title":"FP3O: Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility","date":"2023-10-08","arxiv_id":"2310.05053","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerate-multi-agent-reinforcement-learning","title":"Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning","date":"2023-10-07","arxiv_id":"2310.04796","repositories_listed":0,"syntology":null},{"url":null,"slug":"deconstructing-cooperation-and-ostracism-via","title":"Deconstructing Cooperation and Ostracism via Multi-Agent Reinforcement Learning","date":"2023-10-06","arxiv_id":"2310.04623","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-confirming-transformer-for-locally","title":"Self-Confirming Transformer for Belief-Conditioned Adaptation in Offline Multi-Agent Reinforcement Learning","date":"2023-10-06","arxiv_id":"2310.04579","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-deep-reinforcement-learning-in","title":"A Review of Deep Reinforcement Learning in Serverless Computing: Function Scheduling and Resource Auto-Scaling","date":"2023-10-05","arxiv_id":"2311.12839","repositories_listed":0,"syntology":null},{"url":null,"slug":"fictitious-cross-play-learning-global-nash","title":"Fictitious Cross-Play: Learning Global Nash Equilibrium in Mixed Cooperative-Competitive Games","date":"2023-10-05","arxiv_id":"2310.03354","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-based-on","title":"Multi-Agent Reinforcement Learning Based on Representational Communication for Large-Scale Traffic Signal Control","date":"2023-10-03","arxiv_id":"2310.02435","repositories_listed":0,"syntology":null},{"url":null,"slug":"composer-scalable-and-robust-modular-policies","title":"COMPOSER: Scalable and Robust Modular Policies for Snake Robots","date":"2023-10-02","arxiv_id":"2310.00871","repositories_listed":0,"syntology":null},{"url":null,"slug":"age-minimization-in-massive-iot-via-uav-swarm","title":"Age Minimization in Massive IoT via UAV Swarm: A Multi-agent Reinforcement Learning Approach","date":"2023-09-26","arxiv_id":"2309.14757","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-reinforcement-learning-for-14","title":"Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles using AutoDRIVE Ecosystem","date":"2023-09-18","arxiv_id":"2309.10007","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-multi-agent-reinforcement-learning-for-3","title":"Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing","date":"2023-09-14","arxiv_id":"2309.08477","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-loss-adjusted-prioritized","title":"Attention Loss Adjusted Prioritized Experience Replay","date":"2023-09-13","arxiv_id":"2309.06684","repositories_listed":0,"syntology":null},{"url":null,"slug":"characterizing-speed-performance-of-multi","title":"Characterizing Speed Performance of Multi-Agent Reinforcement Learning","date":"2023-09-13","arxiv_id":"2309.07108","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-engineered-value-decomposition","title":"Privacy-Engineered Value Decomposition Networks for Cooperative Multi-Agent Reinforcement Learning","date":"2023-09-13","arxiv_id":"2311.06255","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergent-communication-in-multi-agent","title":"Emergent Communication in Multi-Agent Reinforcement Learning for Future Wireless Networks","date":"2023-09-12","arxiv_id":"2309.06021","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-handover-throw-and-catch-with","title":"Dynamic Handover: Throw and Catch with Bimanual Hands","date":"2023-09-11","arxiv_id":"2309.05655","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-world-model-disentanglement-in","title":"Leveraging World Model Disentanglement in Value-Based Multi-Agent Reinforcement Learning","date":"2023-09-08","arxiv_id":"2309.04615","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-flow-control-for-three-dimensional","title":"Active flow control for three-dimensional cylinders through deep reinforcement learning","date":"2023-09-04","arxiv_id":"2309.02462","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-multi-agent-reinforcement-6","title":"Decentralized Multi-agent Reinforcement Learning based State-of-Charge Balancing Strategy for Distributed Energy Storage System","date":"2023-08-29","arxiv_id":"2308.15394","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-multi-agent-target-search-and","title":"Distributed multi-agent target search and tracking with Gaussian process and reinforcement learning","date":"2023-08-29","arxiv_id":"2308.14971","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-diversity-for-cooperative-agents","title":"Policy Diversity for Cooperative Agents","date":"2023-08-28","arxiv_id":"2308.14308","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-progress-in-energy-management-of","title":"Recent Progress in Energy Management of Connected Hybrid Electric Vehicles Using Reinforcement Learning","date":"2023-08-28","arxiv_id":"2308.14602","repositories_listed":0,"syntology":null},{"url":null,"slug":"marl-for-decentralized-electric-vehicle","title":"MARL for Decentralized Electric Vehicle Charging Coordination with V2V Energy Exchange","date":"2023-08-27","arxiv_id":"2308.14111","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-cyber-defence-tactics-from-scratch","title":"Learning Cyber Defence Tactics from Scratch with Multi-Agent Reinforcement Learning","date":"2023-08-25","arxiv_id":"2310.05939","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-distributed-multi-agent","title":"An Efficient Distributed Multi-Agent Reinforcement Learning for EV Charging Network Control","date":"2023-08-24","arxiv_id":"2308.12921","repositories_listed":0,"syntology":null},{"url":null,"slug":"perimeter-control-with-heterogeneous-cordon","title":"Perimeter Control with Heterogeneous Metering Rates for Cordon Signals: A Physics-Regularized Multi-Agent Reinforcement Learning Approach","date":"2023-08-24","arxiv_id":"2308.12985","repositories_listed":0,"syntology":null},{"url":null,"slug":"mimicking-to-dominate-imitation-learning","title":"Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Competitive Games","date":"2023-08-20","arxiv_id":"2308.10188","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-communication-planning-for","title":"Intelligent Communication Planning for Constrained Environmental IoT Sensing with Reinforcement Learning","date":"2023-08-19","arxiv_id":"2308.10124","repositories_listed":0,"syntology":null},{"url":null,"slug":"never-explore-repeatedly-in-multi-agent","title":"Never Explore Repeatedly in Multi-Agent Reinforcement Learning","date":"2023-08-19","arxiv_id":"2308.09909","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-free-algorithm-with-improved-sample","title":"Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games","date":"2023-08-17","arxiv_id":"2308.08858","repositories_listed":0,"syntology":null},{"url":null,"slug":"partially-observable-multi-agent-rl-with","title":"Partially Observable Multi-Agent Reinforcement Learning with Information Sharing","date":"2023-08-16","arxiv_id":"2308.08705","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-in-depth-analysis-of-discretization","title":"An In-Depth Analysis of Discretization Methods for Communication Learning using Backpropagation with Multi-Agent Reinforcement Learning","date":"2023-08-09","arxiv_id":"2308.04938","repositories_listed":0,"syntology":null},{"url":null,"slug":"graphcc-a-practical-graph-learning-based","title":"GraphCC: A Practical Graph Learning-based Approach to Congestion Control in Datacenters","date":"2023-08-09","arxiv_id":"2308.04905","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalability-of-message-encoding-techniques","title":"Scalability of Message Encoding Techniques for Continuous Communication Learned with Multi-Agent Reinforcement Learning","date":"2023-08-09","arxiv_id":"2308.04844","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-decentralized-q-learning-two","title":"Unsynchronized Decentralized Q-Learning: Two Timescale Analysis By Persistence","date":"2023-08-07","arxiv_id":"2308.03239","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-driven-multi-agent-reinforcement","title":"Knowledge-Driven Multi-Agent Reinforcement Learning for Computation Offloading in Cybertwin-Enabled Internet of Vehicles","date":"2023-08-04","arxiv_id":"2308.02603","repositories_listed":0,"syntology":null},{"url":null,"slug":"marlim-multi-agent-reinforcement-learning-for","title":"MARLIM: Multi-Agent Reinforcement Learning for Inventory Management","date":"2023-08-03","arxiv_id":"2308.01649","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-multi-agent-reinforcement-learning-1","title":"Quantum Multi-Agent Reinforcement Learning for Autonomous Mobility Cooperation","date":"2023-08-03","arxiv_id":"2308.01519","repositories_listed":0,"syntology":null},{"url":null,"slug":"esp-exploiting-symmetry-prior-for-multi-agent","title":"ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning","date":"2023-07-30","arxiv_id":"2307.16186","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-electric-vehicle-balancing-of","title":"Robust Electric Vehicle Balancing of Autonomous Mobility-On-Demand System: A Multi-Agent Reinforcement Learning Approach","date":"2023-07-30","arxiv_id":"2307.16228","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-international-climate-policy-via-1","title":"Improving International Climate Policy via Mutually Conditional Binding Commitments","date":"2023-07-26","arxiv_id":"2307.14266","repositories_listed":0,"syntology":null},{"url":null,"slug":"consensus-based-participatory-budgeting-for","title":"Consensus-based Participatory Budgeting for Legitimacy: Decision Support via Multi-agent Reinforcement Learning","date":"2023-07-24","arxiv_id":"2307.12915","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-adaptive-formation-via","title":"Decentralized Adaptive Formation via Consensus-Oriented Multi-Agent Communication","date":"2023-07-23","arxiv_id":"2307.12287","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-multi-agent-reinforcement","title":"An Analysis of Multi-Agent Reinforcement Learning for Decentralized Inventory Control Systems","date":"2023-07-21","arxiv_id":"2307.11432","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-tales-of-platoon-intelligence-for","title":"Two Tales of Platoon Intelligence for Autonomous Mobility Control: Enabling Deep Learning Recipes","date":"2023-07-19","arxiv_id":"2307.09711","repositories_listed":0,"syntology":null},{"url":null,"slug":"qmnet-importance-aware-message-exchange-for","title":"QMNet: Importance-Aware Message Exchange for Decentralized Multi-Agent Reinforcement Learning","date":"2023-07-18","arxiv_id":"2307.09051","repositories_listed":0,"syntology":null},{"url":null,"slug":"basal-bolus-advisor-for-type-1-diabetes-t1d","title":"Basal-Bolus Advisor for Type 1 Diabetes (T1D) Patients Using Multi-Agent Reinforcement Learning (RL) Methodology","date":"2023-07-17","arxiv_id":"2307.08897","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-stationary-policy-learning-for-multi","title":"Non-Stationary Policy Learning for Multi-Timescale Multi-Agent Reinforcement Learning","date":"2023-07-17","arxiv_id":"2307.08794","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-adversarial-attacks-on-online-multi","title":"Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning","date":"2023-07-15","arxiv_id":"2307.07670","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multiple-coordinated-agents-under","title":"Learning Multiple Coordinated Agents under Directed Acyclic Graph Constraints","date":"2023-07-13","arxiv_id":"2307.07529","repositories_listed":0,"syntology":null},{"url":null,"slug":"control-as-probabilistic-inference-as-an","title":"Control as Probabilistic Inference as an Emergent Communication Mechanism in Multi-Agent Reinforcement Learning","date":"2023-07-11","arxiv_id":"2307.05004","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-conservatism-diffusion-policies-in","title":"Beyond Conservatism: Diffusion Policies in Offline Multi-agent Reinforcement Learning","date":"2023-07-04","arxiv_id":"2307.01472","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergent-resource-exchange-and-tolerated","title":"Emergent Resource Exchange and Tolerated Theft Behavior using Multi-Agent Reinforcement Learning","date":"2023-07-04","arxiv_id":"2307.01862","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-the-robustness-of-qmix-against","title":"Enhancing the Robustness of QMIX against State-adversarial Attacks","date":"2023-07-03","arxiv_id":"2307.00907","repositories_listed":0,"syntology":null},{"url":null,"slug":"theory-of-mind-as-intrinsic-motivation-for","title":"Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning","date":"2023-07-03","arxiv_id":"2307.01158","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-multi-agent-reinforcement-5","title":"Decentralized Multi-Agent Reinforcement Learning with Global State Prediction","date":"2023-06-22","arxiv_id":"2306.12926","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-multi-agent-learning-for","title":"Cooperative Multi-Agent Learning for Navigation via Structured State Abstraction","date":"2023-06-20","arxiv_id":"2306.11336","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-size-message-scheduling-for-multi","title":"Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth","date":"2023-06-16","arxiv_id":"2306.10134","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-multi-agent-reinforcement-learning","title":"Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization","date":"2023-06-15","arxiv_id":"2306.08900","repositories_listed":0,"syntology":null},{"url":null,"slug":"density-aware-reinforcement-learning-to","title":"Density-Aware Reinforcement Learning to Optimise Energy Efficiency in UAV-Assisted Networks","date":"2023-06-14","arxiv_id":"2306.08785","repositories_listed":0,"syntology":null}],"record_sha256":"1f8663ee0e4f4fecf27a83c45872f4106a9f5754a1d8153d537d29eb45699306","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}