{"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/6","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":6,"pages_in_order":18,"rows_per_page":100,"rows":[501,600],"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/5","next":"/task/multi-agent-reinforcement-learning/papers/7","papers":[{"url":"/paper/qbso-fs-a-reinforcement-learning-based-bee","slug":"qbso-fs-a-reinforcement-learning-based-bee","title":"QBSO-FS: A Reinforcement Learning Based Bee Swarm Optimization Metaheuristic for Feature Selection","date":"2019-05-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cityflow-a-multi-agent-reinforcement-learning","slug":"cityflow-a-multi-agent-reinforcement-learning","title":"CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario","date":"2019-05-13","arxiv_id":"1905.05217","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cityflow-a-multi-agent-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1905.05217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05217"}},"official":{"repos":["cityflow-project/CityFlow"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/concurrent-meta-reinforcement-learning","slug":"concurrent-meta-reinforcement-learning","title":"Concurrent Meta Reinforcement Learning","date":"2019-03-07","arxiv_id":"1903.02710","repositories_listed":1,"syntology":null},{"url":"/paper/a-cooperative-multi-agent-reinforcement","slug":"a-cooperative-multi-agent-reinforcement","title":"A Cooperative Multi-Agent Reinforcement Learning Framework for Resource Balancing in Complex Logistics Network","date":"2019-03-02","arxiv_id":"1903.00714","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-schedule-communication-in-multi","slug":"learning-to-schedule-communication-in-multi","title":"Learning to Schedule Communication in Multi-agent Reinforcement Learning","date":"2019-02-05","arxiv_id":"1902.01554","repositories_listed":1,"syntology":null},{"url":"/paper/minmax-optimization-stable-limit-points-of","slug":"minmax-optimization-stable-limit-points-of","title":"What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?","date":"2019-02-02","arxiv_id":"1902.00618","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-generalized-recursive-reasoning","slug":"multi-agent-generalized-recursive-reasoning","title":"Modelling Bounded Rationality in Multi-Agent Interactions by Generalized Recursive Reasoning","date":"2019-01-26","arxiv_id":"1901.09216","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multi-agent-generalized-recursive-reasoning#ran","syntology_url":"https://syntology.ai/paper/1901.09216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.09216"}},"official":{"repos":["ying-wen/gr2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-multi-agent-reinforcement-learning-with","slug":"deep-multi-agent-reinforcement-learning-with","title":"Deep Multi-Agent Reinforcement Learning with Relevance Graphs","date":"2018-11-30","arxiv_id":"1811.12557","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/deep-multi-agent-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/1811.12557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12557"}},"official":{"repos":["tegg89/magnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/bayesian-action-decoder-for-deep-multi-agent","slug":"bayesian-action-decoder-for-deep-multi-agent","title":"Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning","date":"2018-11-04","arxiv_id":"1811.01458","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-common-knowledge-reinforcement","slug":"multi-agent-common-knowledge-reinforcement","title":"Multi-Agent Common Knowledge Reinforcement Learning","date":"2018-10-27","arxiv_id":"1810.11702","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-agent-common-knowledge-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1810.11702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.11702"}},"official":{"repos":["schroederdewitt/mackrl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/m3rl-mind-aware-multi-agent-management-1","slug":"m3rl-mind-aware-multi-agent-management-1","title":"M$^3$RL: Mind-aware Multi-agent Management Reinforcement Learning","date":"2018-09-29","arxiv_id":"1810.00147","repositories_listed":1,"syntology":null},{"url":"/paper/cm3-cooperative-multi-goal-multi-stage-multi","slug":"cm3-cooperative-multi-goal-multi-stage-multi","title":"CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning","date":"2018-09-13","arxiv_id":"1809.05188","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cm3-cooperative-multi-goal-multi-stage-multi#ran","syntology_url":"https://syntology.ai/paper/1809.05188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.05188"}},"official":{"repos":["011235813/cm3"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/negative-update-intervals-in-deep-multi-agent","slug":"negative-update-intervals-in-deep-multi-agent","title":"Negative Update Intervals in Deep Multi-Agent Reinforcement Learning","date":"2018-09-13","arxiv_id":"1809.05096","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-share-and-hide-intentions-using","slug":"learning-to-share-and-hide-intentions-using","title":"Learning to Share and Hide Intentions using Information Regularization","date":"2018-08-06","arxiv_id":"1808.02093","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-a-report","slug":"multi-agent-reinforcement-learning-a-report","title":"Multi-Agent Reinforcement Learning: A Report on Challenges and Approaches","date":"2018-07-25","arxiv_id":"1807.09427","repositories_listed":1,"syntology":null},{"url":"/paper/emergent-communication-through-negotiation","slug":"emergent-communication-through-negotiation","title":"Emergent Communication through Negotiation","date":"2018-04-11","arxiv_id":"1804.03980","repositories_listed":1,"syntology":null},{"url":"/paper/towards-learning-transferable-conversational","slug":"towards-learning-transferable-conversational","title":"Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling","date":"2018-03-31","arxiv_id":"1804.00146","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-others-using-oneself-in-multi-agent","slug":"modeling-others-using-oneself-in-multi-agent","title":"Modeling Others using Oneself in Multi-Agent Reinforcement Learning","date":"2018-02-26","arxiv_id":"1802.09640","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-gather-without-communication","slug":"learning-to-gather-without-communication","title":"Learning to Gather without Communication","date":"2018-02-21","arxiv_id":"1802.07834","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-large-scale-fleet-management-via","slug":"efficient-large-scale-fleet-management-via","title":"Efficient Collaborative Multi-Agent Deep Reinforcement Learning for Large-Scale Fleet Management","date":"2018-02-18","arxiv_id":"1802.06444","repositories_listed":1,"syntology":null},{"url":"/paper/prosocial-learning-agents-solve-generalized","slug":"prosocial-learning-agents-solve-generalized","title":"Prosocial learning agents solve generalized Stag Hunts better than selfish ones","date":"2017-09-08","arxiv_id":"1709.02865","repositories_listed":1,"syntology":null},{"url":"/paper/lenient-multi-agent-deep-reinforcement","slug":"lenient-multi-agent-deep-reinforcement","title":"Lenient Multi-Agent Deep Reinforcement Learning","date":"2017-07-14","arxiv_id":"1707.04402","repositories_listed":1,"syntology":null},{"url":null,"slug":"a-learning-framework-for-cooperative","title":"A Learning Framework For Cooperative Collision Avoidance of UAV Swarms Leveraging Domain Knowledge","date":"2025-07-15","arxiv_id":"2507.10913","repositories_listed":0,"syntology":null},{"url":null,"slug":"artificial-generals-intelligence-mastering","title":"Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning","date":"2025-07-09","arxiv_id":"2507.06825","repositories_listed":0,"syntology":null},{"url":null,"slug":"center-of-gravity-guided-focusing-influence","title":"Center of Gravity-Guided Focusing Influence Mechanism for Multi-Agent Reinforcement Learning","date":"2025-06-24","arxiv_id":"2506.19417","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-bilateral-team-formation-in","title":"Learning Bilateral Team Formation in Cooperative Multi-Agent Reinforcement Learning","date":"2025-06-24","arxiv_id":"2506.20039","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-for-28","title":"Multi-Agent Reinforcement Learning for Autonomous Multi-Satellite Earth Observation: A Realistic Case Study","date":"2025-06-18","arxiv_id":"2506.15207","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-reinsurance-treaty-bidding-via-multi","title":"Dynamic Reinsurance Treaty Bidding via Multi-Agent Reinforcement Learning","date":"2025-06-16","arxiv_id":"2506.13113","repositories_listed":0,"syntology":null},{"url":null,"slug":"marco-hardware-aware-neural-architecture","title":"MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering","date":"2025-06-16","arxiv_id":"2506.13755","repositories_listed":0,"syntology":null},{"url":null,"slug":"homeostatic-coupling-for-prosocial-behavior","title":"Homeostatic Coupling for Prosocial Behavior","date":"2025-06-15","arxiv_id":"2506.12894","repositories_listed":0,"syntology":null},{"url":null,"slug":"trust-marl-trust-based-multi-agent","title":"Trust-MARL: Trust-Based Multi-Agent Reinforcement Learning Framework for Cooperative On-Ramp Merging Control in Heterogeneous Traffic Flow","date":"2025-06-14","arxiv_id":"2506.12600","repositories_listed":0,"syntology":null},{"url":null,"slug":"wasserstein-barycenter-consensus-for","title":"Wasserstein-Barycenter Consensus for Cooperative Multi-Agent Reinforcement Learning","date":"2025-06-14","arxiv_id":"2506.12497","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-language-models-advancing","title":"Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation","date":"2025-06-11","arxiv_id":"2506.09331","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-is-diversity-rewarded-in-cooperative","title":"When Is Diversity Rewarded in Cooperative Multi-Agent Learning?","date":"2025-06-11","arxiv_id":"2506.09434","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-08149","title":"Ego-centric Learning of Communicative World Models for Autonomous Driving","date":"2025-06-09","arxiv_id":"2506.08149","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralizing-multi-agent-reinforcement","title":"Decentralizing Multi-Agent Reinforcement Learning with Temporal Causal Information","date":"2025-06-09","arxiv_id":"2506.07829","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-as-individuals-evolve-as-a-team-multi","title":"Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments","date":"2025-06-08","arxiv_id":"2506.07232","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-optimization-for-continuous-time","title":"Policy Optimization for Continuous-time Linear-Quadratic Graphon Mean Field Games","date":"2025-06-06","arxiv_id":"2506.05894","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-marl-based-approach-for-easing-mas","title":"A MARL-based Approach for Easing MAS Organization Engineering","date":"2025-06-05","arxiv_id":"2506.05437","repositories_listed":0,"syntology":null},{"url":null,"slug":"cora-coalitional-rational-advantage","title":"CORA: Coalitional Rational Advantage Decomposition for Multi-Agent Policy Gradients","date":"2025-06-03","arxiv_id":"2506.04265","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-mix-enhancing-sample-efficiency-in","title":"Ensemble-MIX: Enhancing Sample Efficiency in Multi-Agent RL Using Ensemble Methods","date":"2025-06-03","arxiv_id":"2506.02841","repositories_listed":0,"syntology":null},{"url":null,"slug":"lamarl-llm-aided-multi-agent-reinforcement","title":"LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation","date":"2025-06-02","arxiv_id":"2506.01538","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-dependency-graphs-for-globally-optimal","title":"Action Dependency Graphs for Globally Optimal Coordinated Reinforcement Learning","date":"2025-06-01","arxiv_id":"2506.00797","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-guided-multi-agent-learning-in","title":"Language-Guided Multi-Agent Learning in Simulations: A Unified Framework and Evaluation","date":"2025-06-01","arxiv_id":"2506.04251","repositories_listed":0,"syntology":null},{"url":null,"slug":"rlae-reinforcement-learning-assisted-ensemble","title":"RLAE: Reinforcement Learning-Assisted Ensemble for LLMs","date":"2025-05-31","arxiv_id":"2506.00439","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-structure-in-mappings-an-approach","title":"Information Structure in Mappings: An Approach to Learning, Representation, and Generalisation","date":"2025-05-29","arxiv_id":"2505.23960","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-independent-messaging-for","title":"Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning","date":"2025-05-28","arxiv_id":"2505.21985","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-in-4","title":"Multi-Agent Reinforcement Learning in Cybersecurity: From Fundamentals to Applications","date":"2025-05-26","arxiv_id":"2505.19837","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-challenge-of-hidden-gifts-in-multi-agent","title":"The challenge of hidden gifts in multi-agent reinforcement learning","date":"2025-05-26","arxiv_id":"2505.20579","repositories_listed":0,"syntology":null},{"url":null,"slug":"agent-based-decentralized-energy-management","title":"Agent-Based Decentralized Energy Management of EV Charging Station with Solar Photovoltaics via Multi-Agent Reinforcement Learning","date":"2025-05-24","arxiv_id":"2505.18750","repositories_listed":0,"syntology":null},{"url":null,"slug":"edgeagentx-a-novel-framework-for-agentic-ai","title":"EdgeAgentX: A Novel Framework for Agentic AI at the Edge in Military Communication Networks","date":"2025-05-24","arxiv_id":"2505.18457","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-time-global-optimality-convergence-in","title":"Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning","date":"2025-05-24","arxiv_id":"2505.18433","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-real-world-cooperative-and-competitive","title":"Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teams","date":"2025-05-20","arxiv_id":"2505.13834","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-sight-range-selection-in-multi-agent","title":"Dynamic Sight Range Selection in Multi-Agent Reinforcement Learning","date":"2025-05-19","arxiv_id":"2505.12811","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11100","title":"Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors","date":"2025-05-16","arxiv_id":"2505.11100","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11311","title":"Explaining Strategic Decisions in Multi-Agent Reinforcement Learning for Aerial Combat Tactics","date":"2025-05-16","arxiv_id":"2505.11311","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11461","title":"Signal attenuation enables scalable decentralized multi-agent reinforcement learning over networks","date":"2025-05-16","arxiv_id":"2505.11461","repositories_listed":0,"syntology":null},{"url":null,"slug":"fixing-incomplete-value-function","title":"Fixing Incomplete Value Function Decomposition for Multi-Agent Reinforcement Learning","date":"2025-05-15","arxiv_id":"2505.10484","repositories_listed":0,"syntology":null},{"url":null,"slug":"community-based-multi-agent-reinforcement","title":"Community-based Multi-Agent Reinforcement Learning with Transfer and Active Exploration","date":"2025-05-14","arxiv_id":"2505.09756","repositories_listed":0,"syntology":null},{"url":null,"slug":"credit-assignment-and-efficient-exploration","title":"Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning","date":"2025-05-13","arxiv_id":"2505.08630","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-aerial-combat-tactics-through","title":"Enhancing Aerial Combat Tactics through Hierarchical Multi-Agent Reinforcement Learning","date":"2025-05-13","arxiv_id":"2505.08995","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-multi-agent-reinforcement-learning-1","title":"Scaling Multi Agent Reinforcement Learning for Underwater Acoustic Tracking via Autonomous Vehicles","date":"2025-05-13","arxiv_id":"2505.08222","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-source-plume-tracing-via-multi-agent","title":"Multi-source Plume Tracing via Multi-Agent Reinforcement Learning","date":"2025-05-12","arxiv_id":"2505.08825","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-agent-reinforcement-learning-approach-2","title":"A Multi-Agent Reinforcement Learning Approach for Cooperative Air-Ground-Human Crowdsensing in Emergency Rescue","date":"2025-05-11","arxiv_id":"2505.06997","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-level-mean-field-dynamic-grouping-for","title":"Bi-level Mean Field: Dynamic Grouping for Large-Scale MARL","date":"2025-05-10","arxiv_id":"2505.06706","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-power-control-protocol-for-in","title":"Learning Power Control Protocol for In-Factory 6G Subnetworks","date":"2025-05-09","arxiv_id":"2505.05967","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-multi-agent-reinforcement-learning-3","title":"Offline Multi-agent Reinforcement Learning via Score Decomposition","date":"2025-05-09","arxiv_id":"2505.05968","repositories_listed":0,"syntology":null},{"url":null,"slug":"ccl-collaborative-curriculum-learning-for","title":"CCL: Collaborative Curriculum Learning for Sparse-Reward Multi-Agent Reinforcement Learning via Co-evolutionary Task Evolution","date":"2025-05-08","arxiv_id":"2505.07854","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-q-network-dqn-multi-agent-reinforcement","title":"Deep Q-Network (DQN) multi-agent reinforcement learning (MARL) for Stock Trading","date":"2025-05-06","arxiv_id":"2505.03949","repositories_listed":0,"syntology":null},{"url":null,"slug":"rainbow-delay-compensation-a-multi-agent","title":"Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Delayed Observation","date":"2025-05-06","arxiv_id":"2505.03586","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-scale-fading-aware-resource-allocation","title":"Small-Scale-Fading-Aware Resource Allocation in Wireless Federated Learning","date":"2025-05-06","arxiv_id":"2505.03533","repositories_listed":0,"syntology":null},{"url":null,"slug":"securing-5g-and-beyond-enabled-uav-networks","title":"Securing 5G and Beyond-Enabled UAV Networks: Resilience Through Multiagent Learning and Transformers Detection","date":"2025-05-03","arxiv_id":"2505.01885","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergence-of-roles-in-robotic-teams-with","title":"Emergence of Roles in Robotic Teams with Model Sharing and Limited Communication","date":"2025-05-01","arxiv_id":"2505.00540","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-and-efficient-cav-lane-changing-using","title":"Safe and Efficient CAV Lane Changing using Decentralised Safety Shields","date":"2025-04-30","arxiv_id":"2505.01453","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-bottom-up-flexibility-provision-from","title":"Safe Bottom-Up Flexibility Provision from Distributed Energy Resources","date":"2025-04-29","arxiv_id":"2504.20529","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-multi-agent-safe-optimal-control-with","title":"Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL","date":"2025-04-21","arxiv_id":"2504.15425","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-thinking-in-llms-via-multi-agent","title":"Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey","date":"2025-04-20","arxiv_id":"2504.14520","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-lattice-boltzmann-closures-through","title":"Optimal Lattice Boltzmann Closures through Multi-Agent Reinforcement Learning","date":"2025-04-19","arxiv_id":"2504.14422","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-assignment-and-exploration-optimization","title":"Task Assignment and Exploration Optimization for Low Altitude UAV Rescue via Generative AI Enhanced Multi-agent Reinforcement Learning","date":"2025-04-18","arxiv_id":"2504.13554","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-simulation","title":"Multi-Agent Reinforcement Learning Simulation for Environmental Policy Synthesis","date":"2025-04-17","arxiv_id":"2504.12777","repositories_listed":0,"syntology":null},{"url":null,"slug":"qllm-do-we-really-need-a-mixing-network-for","title":"QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?","date":"2025-04-17","arxiv_id":"2504.12961","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-for-25","title":"Multi-Agent Reinforcement Learning for Greenhouse Gas Offset Credit Markets","date":"2025-04-15","arxiv_id":"2504.11258","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-for-26","title":"Multi-Agent Reinforcement Learning for Decentralized Reservoir Management via Murmuration Intelligence","date":"2025-04-15","arxiv_id":"2504.11569","repositories_listed":0,"syntology":null},{"url":null,"slug":"achieving-optimal-tissue-repair-through-marl","title":"Achieving Optimal Tissue Repair Through MARL with Reward Shaping and Curriculum Learning","date":"2025-04-14","arxiv_id":"2504.10677","repositories_listed":0,"syntology":null},{"url":null,"slug":"belief-states-for-cooperative-multi-agent","title":"Belief States for Cooperative Multi-Agent Reinforcement Learning under Partial Observability","date":"2025-04-11","arxiv_id":"2504.08417","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-augmented-inverse-reinforcement","title":"Attention-Augmented Inverse Reinforcement Learning with Graph Convolutions for Multi-Agent Task Allocation","date":"2025-04-07","arxiv_id":"2504.05045","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-hierarchical-reinforcement-learning","title":"Federated Hierarchical Reinforcement Learning for Adaptive Traffic Signal Control","date":"2025-04-07","arxiv_id":"2504.05553","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyprl-reinforcement-learning-of-control","title":"HypRL: Reinforcement Learning of Control Policies for Hyperproperties","date":"2025-04-07","arxiv_id":"2504.04675","repositories_listed":0,"syntology":null},{"url":null,"slug":"orbitzoo-multi-agent-reinforcement-learning","title":"OrbitZoo: Multi-Agent Reinforcement Learning Environment for Orbital Dynamics","date":"2025-04-05","arxiv_id":"2504.04160","repositories_listed":0,"syntology":null},{"url":null,"slug":"fair-dynamic-spectrum-access-via-fully","title":"Fair Dynamic Spectrum Access via Fully Decentralized Multi-Agent Reinforcement Learning","date":"2025-03-31","arxiv_id":"2503.24296","repositories_listed":0,"syntology":null},{"url":null,"slug":"late-breaking-results-breaking-symmetry","title":"Late Breaking Results: Breaking Symmetry- Unconventional Placement of Analog Circuits using Multi-Level Multi-Agent Reinforcement Learning","date":"2025-03-29","arxiv_id":"2503.22958","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-for-graph","title":"Multi-Agent Reinforcement Learning for Graph Discovery in D2D-Enabled Federated Learning","date":"2025-03-29","arxiv_id":"2503.23218","repositories_listed":0,"syntology":null},{"url":null,"slug":"markov-potential-game-construction-and-multi","title":"Markov Potential Game Construction and Multi-Agent Reinforcement Learning with Applications to Autonomous Driving","date":"2025-03-28","arxiv_id":"2503.22867","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-optimization-and-multi-agent","title":"Policy Optimization and Multi-agent Reinforcement Learning for Mean-variance Team Stochastic Games","date":"2025-03-28","arxiv_id":"2503.22779","repositories_listed":0,"syntology":null},{"url":null,"slug":"flip-learning-weakly-supervised-erase-to","title":"Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound","date":"2025-03-26","arxiv_id":"2503.20685","repositories_listed":0,"syntology":null},{"url":null,"slug":"harmonia-a-multi-agent-reinforcement-learning","title":"Harmonia: A Multi-Agent Reinforcement Learning Approach to Data Placement and Migration in Hybrid Storage Systems","date":"2025-03-26","arxiv_id":"2503.20507","repositories_listed":0,"syntology":null},{"url":null,"slug":"abstracting-geo-specific-terrains-to-scale-up","title":"Abstracting Geo-specific Terrains to Scale Up Reinforcement Learning","date":"2025-03-25","arxiv_id":"2503.20078","repositories_listed":0,"syntology":null},{"url":null,"slug":"lero-llm-driven-evolutionary-framework-with","title":"LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning","date":"2025-03-25","arxiv_id":"2503.21807","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-path-planning-and-cost-minimization","title":"Optimal Path Planning and Cost Minimization for a Drone Delivery System Via Model Predictive Control","date":"2025-03-25","arxiv_id":"2503.19699","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multi-robot-coordination-through","title":"Learning Multi-Robot Coordination through Locality-Based Factorized Multi-Agent Actor-Critic Algorithm","date":"2025-03-24","arxiv_id":"2503.18816","repositories_listed":0,"syntology":null}],"record_sha256":"9fd82a447fc96ecbbde845c99ad8abb65240fe05a69ca68432c28a8ddd3b7140","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}