{"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/2","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":2,"pages_in_order":18,"rows_per_page":100,"rows":[101,200],"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","next":"/task/multi-agent-reinforcement-learning/papers/3","papers":[{"url":"/paper/unreal-map-unreal-engine-based-general","slug":"unreal-map-unreal-engine-based-general","title":"Unreal-MAP: Unreal-Engine-Based General Platform for Multi-Agent Reinforcement Learning","date":"2025-03-20","arxiv_id":"2503.15947","repositories_listed":1,"syntology":null},{"url":"/paper/had-gen-human-like-and-diverse-driving","slug":"had-gen-human-like-and-diverse-driving","title":"HAD-Gen: Human-like and Diverse Driving Behavior Modeling for Controllable Scenario Generation","date":"2025-03-19","arxiv_id":"2503.15049","repositories_listed":1,"syntology":null},{"url":"/paper/socialjax-an-evaluation-suite-for-multi-agent","slug":"socialjax-an-evaluation-suite-for-multi-agent","title":"SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas","date":"2025-03-18","arxiv_id":"2503.14576","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/socialjax-an-evaluation-suite-for-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2503.14576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14576"}},"official":{"repos":["cooperativex/socialjax"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-generalist-hanabi-agent","slug":"a-generalist-hanabi-agent","title":"A Generalist Hanabi Agent","date":"2025-03-17","arxiv_id":"2503.14555","repositories_listed":1,"syntology":null},{"url":"/paper/rema-learning-to-meta-think-for-llms-with","slug":"rema-learning-to-meta-think-for-llms-with","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","date":"2025-03-12","arxiv_id":"2503.09501","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-multi-uav-collaboration-marl","slug":"towards-robust-multi-uav-collaboration-marl","title":"Towards Robust Multi-UAV Collaboration: MARL with Noise-Resilient Communication and Attention Mechanisms","date":"2025-03-04","arxiv_id":"2503.02913","repositories_listed":1,"syntology":null},{"url":"/paper/trajectory-class-aware-multi-agent","slug":"trajectory-class-aware-multi-agent","title":"Trajectory-Class-Aware Multi-Agent Reinforcement Learning","date":"2025-03-03","arxiv_id":"2503.01440","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/trajectory-class-aware-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2503.01440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01440"}},"official":{"repos":["aailab-kaist/trama"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/real-world-deployment-and-assessment-of-a","slug":"real-world-deployment-and-assessment-of-a","title":"Real-World Deployment and Assessment of a Multi-Agent Reinforcement Learning-Based Variable Speed Limit Control System","date":"2025-03-02","arxiv_id":"2503.01017","repositories_listed":1,"syntology":null},{"url":"/paper/exponential-topology-enabled-scalable","slug":"exponential-topology-enabled-scalable","title":"Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning","date":"2025-02-27","arxiv_id":"2502.19717","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":1,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exponential-topology-enabled-scalable#ran","syntology_url":"https://syntology.ai/paper/2502.19717","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19717"}},"official":{"repos":["lxxxxr/expocomm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["community","official","unlocated"]}}},{"url":"/paper/routerl-multi-agent-reinforcement-learning","slug":"routerl-multi-agent-reinforcement-learning","title":"RouteRL: Multi-agent reinforcement learning framework for urban route choice with autonomous vehicles","date":"2025-02-27","arxiv_id":"2502.20065","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/routerl-multi-agent-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2502.20065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20065"}},"official":{"repos":["coexistence-project/routerl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pmat-optimizing-action-generation-order-in","slug":"pmat-optimizing-action-generation-order-in","title":"PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning","date":"2025-02-23","arxiv_id":"2502.16496","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-language-multi-agent-learning-with","slug":"enhancing-language-multi-agent-learning-with","title":"Enhancing Language Multi-Agent Learning with Multi-Agent Credit Re-Assignment for Interactive Environment Generalization","date":"2025-02-20","arxiv_id":"2502.14496","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-solve-the-min-max-mixed-shelves","slug":"learning-to-solve-the-min-max-mixed-shelves","title":"Learning to Solve the Min-Max Mixed-Shelves Picker-Routing Problem via Hierarchical and Parallel Decoding","date":"2025-02-14","arxiv_id":"2502.10233","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-to-solve-the-min-max-mixed-shelves#ran","syntology_url":"https://syntology.ai/paper/2502.10233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.10233"}},"official":{"repos":["ltluttmann/marl4msprp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/training-language-models-for-social-deduction","slug":"training-language-models-for-social-deduction","title":"Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning","date":"2025-02-09","arxiv_id":"2502.06060","repositories_listed":1,"syntology":null},{"url":"/paper/an-extended-benchmarking-of-multi-agent","slug":"an-extended-benchmarking-of-multi-agent","title":"An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks","date":"2025-02-07","arxiv_id":"2502.04773","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-extended-benchmarking-of-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2502.04773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04773"}},"official":{"repos":["ailabdsunipi/pymarlzooplus"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-meta-coordination-graphs-for-multi-agent","slug":"deep-meta-coordination-graphs-for-multi-agent","title":"Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning","date":"2025-02-06","arxiv_id":"2502.04028","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-with-focal","slug":"multi-agent-reinforcement-learning-with-focal","title":"Multi-Agent Reinforcement Learning with Focal Diversity Optimization","date":"2025-02-06","arxiv_id":"2502.04492","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/multi-agent-reinforcement-learning-with-focal#ran","syntology_url":"https://syntology.ai/paper/2502.04492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04492"}},"official":{"repos":["sftekin/rl-focal"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/wolfpack-adversarial-attack-for-robust-multi","slug":"wolfpack-adversarial-attack-for-robust-multi","title":"Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning","date":"2025-02-05","arxiv_id":"2502.02844","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/wolfpack-adversarial-attack-for-robust-multi#ran","syntology_url":"https://syntology.ai/paper/2502.02844","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02844"}},"official":{"repos":["sunwoolee0504/wall"],"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/the-composite-task-challenge-for-cooperative","slug":"the-composite-task-challenge-for-cooperative","title":"The Composite Task Challenge for Cooperative Multi-Agent Reinforcement Learning","date":"2025-02-01","arxiv_id":"2502.00345","repositories_listed":1,"syntology":null},{"url":"/paper/expert-free-online-transfer-learning-in-multi-1","slug":"expert-free-online-transfer-learning-in-multi-1","title":"Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning","date":"2025-01-26","arxiv_id":"2501.15495","repositories_listed":1,"syntology":null},{"url":"/paper/improving-retrieval-augmented-generation","slug":"improving-retrieval-augmented-generation","title":"Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning","date":"2025-01-25","arxiv_id":"2501.15228","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-retrieval-augmented-generation#ran","syntology_url":"https://syntology.ai/paper/2501.15228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15228"}},"official":{"repos":["chenyiqun/mmoa-rag"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scalable-safe-multi-agent-reinforcement","slug":"scalable-safe-multi-agent-reinforcement","title":"Scalable Safe Multi-Agent Reinforcement Learning for Multi-Agent System","date":"2025-01-23","arxiv_id":"2501.13727","repositories_listed":1,"syntology":null},{"url":"/paper/wfcrl-a-multi-agent-reinforcement-learning","slug":"wfcrl-a-multi-agent-reinforcement-learning","title":"WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control","date":"2025-01-23","arxiv_id":"2501.13592","repositories_listed":1,"syntology":null},{"url":"/paper/srmt-shared-memory-for-multi-agent-lifelong","slug":"srmt-shared-memory-for-multi-agent-lifelong","title":"SRMT: Shared Memory for Multi-agent Lifelong Pathfinding","date":"2025-01-22","arxiv_id":"2501.13200","repositories_listed":1,"syntology":null},{"url":"/paper/tackling-uncertainties-in-multi-agent","slug":"tackling-uncertainties-in-multi-agent","title":"Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamics","date":"2025-01-21","arxiv_id":"2501.12061","repositories_listed":1,"syntology":null},{"url":"/paper/colorgrid-a-multi-agent-non-stationary","slug":"colorgrid-a-multi-agent-non-stationary","title":"ColorGrid: A Multi-Agent Non-Stationary Environment for Goal Inference and Assistance","date":"2025-01-17","arxiv_id":"2501.10593","repositories_listed":1,"syntology":null},{"url":"/paper/cooperative-patrol-routing-optimizing-urban","slug":"cooperative-patrol-routing-optimizing-urban","title":"Cooperative Patrol Routing: Optimizing Urban Crime Surveillance through Multi-Agent Reinforcement Learning","date":"2025-01-14","arxiv_id":"2501.08020","repositories_listed":1,"syntology":null},{"url":"/paper/camp-collaborative-attention-model-with","slug":"camp-collaborative-attention-model-with","title":"CAMP: Collaborative Attention Model with Profiles for Vehicle Routing Problems","date":"2025-01-06","arxiv_id":"2501.02977","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/camp-collaborative-attention-model-with#ran","syntology_url":"https://syntology.ai/paper/2501.02977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.02977"}},"official":{"repos":["ai4co/camp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/smac-hard-enabling-mixed-opponent-strategy","slug":"smac-hard-enabling-mixed-opponent-strategy","title":"SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC","date":"2024-12-23","arxiv_id":"2412.17707","repositories_listed":1,"syntology":null},{"url":"/paper/air-unifying-individual-and-cooperative","slug":"air-unifying-individual-and-cooperative","title":"AIR: Unifying Individual and Collective Exploration in Cooperative Multi-Agent Reinforcement Learning","date":"2024-12-20","arxiv_id":"2412.15700","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-for-24","slug":"multi-agent-reinforcement-learning-for-24","title":"Multi Agent Reinforcement Learning for Sequential Satellite Assignment Problems","date":"2024-12-20","arxiv_id":"2412.15573","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/multi-agent-reinforcement-learning-for-24#ran","syntology_url":"https://syntology.ai/paper/2412.15573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15573"}},"official":{"repos":["Rainlabuw/rl-enabled-distributed-assignment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-relational-state-abstraction-in","slug":"investigating-relational-state-abstraction-in","title":"Investigating Relational State Abstraction in Collaborative MARL","date":"2024-12-19","arxiv_id":"2412.15388","repositories_listed":1,"syntology":null},{"url":"/paper/a-marl-based-multi-target-tracking-algorithm","slug":"a-marl-based-multi-target-tracking-algorithm","title":"A MARL Based Multi-Target Tracking Algorithm Under Jamming Against Radar","date":"2024-12-17","arxiv_id":"2412.12547","repositories_listed":1,"syntology":null},{"url":"/paper/learn-how-to-query-from-unlabeled-data","slug":"learn-how-to-query-from-unlabeled-data","title":"Learn How to Query from Unlabeled Data Streams in Federated Learning","date":"2024-12-11","arxiv_id":"2412.08138","repositories_listed":1,"syntology":null},{"url":"/paper/augmenting-the-action-space-with-conventions","slug":"augmenting-the-action-space-with-conventions","title":"Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi","date":"2024-12-09","arxiv_id":"2412.06333","repositories_listed":1,"syntology":null},{"url":"/paper/hypermarl-adaptive-hypernetworks-for-multi","slug":"hypermarl-adaptive-hypernetworks-for-multi","title":"HyperMARL: Adaptive Hypernetworks for Multi-Agent RL","date":"2024-12-05","arxiv_id":"2412.04233","repositories_listed":1,"syntology":{"n":26,"n_ran":11,"n_constructed":1,"n_ran_checked":10,"n_instrument":1,"n_unverified":15,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/hypermarl-adaptive-hypernetworks-for-multi#ran","syntology_url":"https://syntology.ai/paper/2412.04233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04233"}},"official":{"repos":["kaleabtessera/hypermarl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":1,"n_ran_no_instrument_failure":10,"n_unverified":15,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-fault-tolerance-in-multi-agent","slug":"towards-fault-tolerance-in-multi-agent","title":"Towards Fault Tolerance in Multi-Agent Reinforcement Learning","date":"2024-11-30","arxiv_id":"2412.00534","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-cooperate-with-humans-using","slug":"learning-to-cooperate-with-humans-using","title":"Learning to Cooperate with Humans using Generative Agents","date":"2024-11-21","arxiv_id":"2411.13934","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/learning-to-cooperate-with-humans-using#ran","syntology_url":"https://syntology.ai/paper/2411.13934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13934"}},"official":{"repos":["lych1233/gamma-human-ai-collaboration"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/investesg-a-multi-agent-reinforcement","slug":"investesg-a-multi-agent-reinforcement","title":"InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma","date":"2024-11-15","arxiv_id":"2411.09856","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-aware-resource-management-for-c-v2x","slug":"semantic-aware-resource-management-for-c-v2x","title":"Semantic-Aware Resource Management for C-V2X Platooning via Multi-Agent Reinforcement Learning","date":"2024-11-07","arxiv_id":"2411.04672","repositories_listed":1,"syntology":null},{"url":"/paper/think-smart-act-smarl-analyzing-probabilistic","slug":"think-smart-act-smarl-analyzing-probabilistic","title":"Think Smart, Act SMARL! Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learning","date":"2024-11-07","arxiv_id":"2411.04867","repositories_listed":1,"syntology":null},{"url":"/paper/adasociety-an-adaptive-environment-with","slug":"adasociety-an-adaptive-environment-with","title":"AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making","date":"2024-11-06","arxiv_id":"2411.03865","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/adasociety-an-adaptive-environment-with#ran","syntology_url":"https://syntology.ai/paper/2411.03865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03865"}},"official":{"repos":["bigai-ai/adasociety"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/toward-finding-strong-pareto-optimal-policies","slug":"toward-finding-strong-pareto-optimal-policies","title":"Toward Finding Strong Pareto Optimal Policies in Multi-Agent Reinforcement Learning","date":"2024-10-25","arxiv_id":"2410.19372","repositories_listed":1,"syntology":null},{"url":"/paper/pytsc-a-unified-platform-for-multi-agent","slug":"pytsc-a-unified-platform-for-multi-agent","title":"PyTSC: A Unified Platform for Multi-Agent Reinforcement Learning in Traffic Signal Control","date":"2024-10-23","arxiv_id":"2410.18202","repositories_listed":1,"syntology":null},{"url":"/paper/evolution-with-opponent-learning-awareness","slug":"evolution-with-opponent-learning-awareness","title":"Evolution of Societies via Reinforcement Learning","date":"2024-10-22","arxiv_id":"2410.17466","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-approach-to-solving-smac-task","slug":"a-new-approach-to-solving-smac-task","title":"A New Approach to Solving SMAC Task: Generating Decision Tree Code from Large Language Models","date":"2024-10-21","arxiv_id":"2410.16024","repositories_listed":1,"syntology":null},{"url":"/paper/cooperation-and-fairness-in-multi-agent","slug":"cooperation-and-fairness-in-multi-agent","title":"Cooperation and Fairness in Multi-Agent Reinforcement Learning","date":"2024-10-19","arxiv_id":"2410.14916","repositories_listed":1,"syntology":null},{"url":"/paper/intersectionzoo-eco-driving-for-benchmarking","slug":"intersectionzoo-eco-driving-for-benchmarking","title":"IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning","date":"2024-10-19","arxiv_id":"2410.15221","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/intersectionzoo-eco-driving-for-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2410.15221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15221"}},"official":{"repos":["mit-wu-lab/IntersectionZoo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kaleidoscope-learnable-masks-for","slug":"kaleidoscope-learnable-masks-for","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","date":"2024-10-11","arxiv_id":"2410.08540","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":2,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/kaleidoscope-learnable-masks-for#ran","syntology_url":"https://syntology.ai/paper/2410.08540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08540"}},"official":{"repos":["lxxxxr/kaleidoscope"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/large-legislative-models-towards-efficient-ai","slug":"large-legislative-models-towards-efficient-ai","title":"Large Legislative Models: Towards Efficient AI Policymaking in Economic Simulations","date":"2024-10-10","arxiv_id":"2410.08345","repositories_listed":1,"syntology":null},{"url":"/paper/optima-optimized-policy-for-intelligent-multi","slug":"optima-optimized-policy-for-intelligent-multi","title":"OPTIMA: Optimized Policy for Intelligent Multi-Agent Systems Enables Coordination-Aware Autonomous Vehicles","date":"2024-10-09","arxiv_id":"2410.18112","repositories_listed":1,"syntology":null},{"url":"/paper/coevolving-with-the-other-you-fine-tuning-llm","slug":"coevolving-with-the-other-you-fine-tuning-llm","title":"Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning","date":"2024-10-08","arxiv_id":"2410.06101","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/coevolving-with-the-other-you-fine-tuning-llm#ran","syntology_url":"https://syntology.ai/paper/2410.06101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06101"}},"official":{"repos":["Harry67Hu/CORY"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cooperative-and-asynchronous-transformer","slug":"cooperative-and-asynchronous-transformer","title":"Cooperative and Asynchronous Transformer-based Mission Planning for Heterogeneous Teams of Mobile Robots","date":"2024-10-08","arxiv_id":"2410.06372","repositories_listed":1,"syntology":null},{"url":"/paper/dashing-for-the-golden-snitch-multi-drone","slug":"dashing-for-the-golden-snitch-multi-drone","title":"Dashing for the Golden Snitch: Multi-Drone Time-Optimal Motion Planning with Multi-Agent Reinforcement Learning","date":"2024-09-25","arxiv_id":"2409.16720","repositories_listed":1,"syntology":null},{"url":"/paper/on-centralized-critics-in-multi-agent","slug":"on-centralized-critics-in-multi-agent","title":"On Centralized Critics in Multi-Agent Reinforcement Learning","date":"2024-08-26","arxiv_id":"2408.14597","repositories_listed":1,"syntology":null},{"url":"/paper/hokoff-real-game-dataset-from-honor-of-kings-1","slug":"hokoff-real-game-dataset-from-honor-of-kings-1","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","date":"2024-08-20","arxiv_id":"2408.10556","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/hokoff-real-game-dataset-from-honor-of-kings-1#ran","syntology_url":"https://syntology.ai/paper/2408.10556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10556"}},"official":{"repos":["tencent-ailab/hokoff"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sustaindc-benchmarking-for-sustainable-data","slug":"sustaindc-benchmarking-for-sustainable-data","title":"SustainDC: Benchmarking for Sustainable Data Center Control","date":"2024-08-14","arxiv_id":"2408.07841","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sustaindc-benchmarking-for-sustainable-data#ran","syntology_url":"https://syntology.ai/paper/2408.07841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07841"}},"official":{"repos":["hewlettpackard/dc-rl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/decentralized-cooperation-in-heterogeneous","slug":"decentralized-cooperation-in-heterogeneous","title":"Enhancing Heterogeneous Multi-Agent Cooperation in Decentralized MARL via GNN-driven Intrinsic Rewards","date":"2024-08-12","arxiv_id":"2408.06503","repositories_listed":1,"syntology":null},{"url":"/paper/qtypemix-enhancing-multi-agent-cooperative","slug":"qtypemix-enhancing-multi-agent-cooperative","title":"QTypeMix: Enhancing Multi-Agent Cooperative Strategies through Heterogeneous and Homogeneous Value Decomposition","date":"2024-08-12","arxiv_id":"2408.07098","repositories_listed":1,"syntology":null},{"url":"/paper/assigning-credit-with-partial-reward","slug":"assigning-credit-with-partial-reward","title":"Assigning Credit with Partial Reward Decoupling in Multi-Agent Proximal Policy Optimization","date":"2024-08-08","arxiv_id":"2408.04295","repositories_listed":1,"syntology":null},{"url":"/paper/2407-21565","slug":"2407-21565","title":"Multi-agent reinforcement learning for the control of three-dimensional Rayleigh-Bénard convection","date":"2024-07-31","arxiv_id":"2407.21565","repositories_listed":1,"syntology":null},{"url":"/paper/quantum-computing-and-neuromorphic-computing","slug":"quantum-computing-and-neuromorphic-computing","title":"Quantum Computing and Neuromorphic Computing for Safe, Reliable, and explainable Multi-Agent Reinforcement Learning: Optimal Control in Autonomous Robotics","date":"2024-07-29","arxiv_id":"2408.03884","repositories_listed":1,"syntology":null},{"url":"/paper/advanced-deep-reinforcement-learning-methods","slug":"advanced-deep-reinforcement-learning-methods","title":"Advanced deep-reinforcement-learning methods for flow control: group-invariant and positional-encoding networks improve learning speed and quality","date":"2024-07-25","arxiv_id":"2407.17822","repositories_listed":1,"syntology":null},{"url":"/paper/reinforced-prompt-personalization-for","slug":"reinforced-prompt-personalization-for","title":"Reinforced Prompt Personalization for Recommendation with Large Language Models","date":"2024-07-24","arxiv_id":"2407.17115","repositories_listed":1,"syntology":null},{"url":"/paper/momaland-a-set-of-benchmarks-for-multi","slug":"momaland-a-set-of-benchmarks-for-multi","title":"MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning","date":"2024-07-23","arxiv_id":"2407.16312","repositories_listed":1,"syntology":null},{"url":"/paper/pogema-a-benchmark-platform-for-cooperative","slug":"pogema-a-benchmark-platform-for-cooperative","title":"POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding","date":"2024-07-20","arxiv_id":"2407.14931","repositories_listed":1,"syntology":null},{"url":"/paper/digital-twin-vehicular-edge-computing-network","slug":"digital-twin-vehicular-edge-computing-network","title":"Digital Twin Vehicular Edge Computing Network: Task Offloading and Resource Allocation","date":"2024-07-16","arxiv_id":"2407.11310","repositories_listed":1,"syntology":null},{"url":"/paper/hypothetical-minds-scaffolding-theory-of-mind","slug":"hypothetical-minds-scaffolding-theory-of-mind","title":"Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models","date":"2024-07-09","arxiv_id":"2407.07086","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hypothetical-minds-scaffolding-theory-of-mind#ran","syntology_url":"https://syntology.ai/paper/2407.07086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07086"}},"official":{"repos":["locross93/hypothetical-minds"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fedmrl-data-heterogeneity-aware-federated","slug":"fedmrl-data-heterogeneity-aware-federated","title":"FedMRL: Data Heterogeneity Aware Federated Multi-agent Deep Reinforcement Learning for Medical Imaging","date":"2024-07-08","arxiv_id":"2407.05800","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-age-of-information-in-vehicular","slug":"optimizing-age-of-information-in-vehicular","title":"Optimizing Age of Information in Vehicular Edge Computing with Federated Graph Neural Network Multi-Agent Reinforcement Learning","date":"2024-07-01","arxiv_id":"2407.02342","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-prototype-aware-learning-for-active","slug":"temporal-prototype-aware-learning-for-active","title":"Temporal Prototype-Aware Learning for Active Voltage Control on Power Distribution Networks","date":"2024-06-25","arxiv_id":"2406.17818","repositories_listed":1,"syntology":null},{"url":"/paper/soft-qmix-integrating-maximum-entropy-for","slug":"soft-qmix-integrating-maximum-entropy-for","title":"Soft-QMIX: Integrating Maximum Entropy For Monotonic Value Function Factorization","date":"2024-06-20","arxiv_id":"2406.13930","repositories_listed":1,"syntology":null},{"url":"/paper/balancing-performance-and-cost-for-two-hop","slug":"balancing-performance-and-cost-for-two-hop","title":"Balancing Performance and Cost for Two-Hop Cooperative Communications: Stackelberg Game and Distributed Multi-Agent Reinforcement Learning","date":"2024-06-17","arxiv_id":"2406.11265","repositories_listed":1,"syntology":null},{"url":"/paper/reconfigurable-intelligent-surface-assisted-28","slug":"reconfigurable-intelligent-surface-assisted-28","title":"Reconfigurable Intelligent Surface Assisted VEC Based on Multi-Agent Reinforcement Learning","date":"2024-06-17","arxiv_id":"2406.11318","repositories_listed":1,"syntology":null},{"url":"/paper/dispelling-the-mirage-of-progress-in-offline","slug":"dispelling-the-mirage-of-progress-in-offline","title":"Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation","date":"2024-06-13","arxiv_id":"2406.09068","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dispelling-the-mirage-of-progress-in-offline#ran","syntology_url":"https://syntology.ai/paper/2406.09068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09068"}},"official":{"repos":["instadeepai/og-marl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/carbon-market-simulation-with-adaptive","slug":"carbon-market-simulation-with-adaptive","title":"Carbon Market Simulation with Adaptive Mechanism Design","date":"2024-06-12","arxiv_id":"2406.07875","repositories_listed":1,"syntology":null},{"url":"/paper/mini-honor-of-kings-a-lightweight-environment","slug":"mini-honor-of-kings-a-lightweight-environment","title":"Mini Honor of Kings: A Lightweight Environment for Multi-Agent Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.03978","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-learning-in-chinese-checkers","slug":"efficient-learning-in-chinese-checkers","title":"Efficient Learning in Chinese Checkers: Comparing Parameter Sharing in Multi-Agent Reinforcement Learning","date":"2024-05-29","arxiv_id":"2405.18733","repositories_listed":1,"syntology":null},{"url":"/paper/individual-contributions-as-intrinsic","slug":"individual-contributions-as-intrinsic","title":"Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning","date":"2024-05-28","arxiv_id":"2405.18110","repositories_listed":1,"syntology":null},{"url":"/paper/pytag-tabletop-games-for-multi-agent","slug":"pytag-tabletop-games-for-multi-agent","title":"PyTAG: Tabletop Games for Multi-Agent Reinforcement Learning","date":"2024-05-28","arxiv_id":"2405.18123","repositories_listed":1,"syntology":null},{"url":"/paper/safe-multi-agent-reinforcement-learning-with","slug":"safe-multi-agent-reinforcement-learning-with","title":"Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Driving","date":"2024-05-28","arxiv_id":"2405.18209","repositories_listed":1,"syntology":null},{"url":"/paper/eqmarl-entangled-quantum-multi-agent","slug":"eqmarl-entangled-quantum-multi-agent","title":"eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels","date":"2024-05-24","arxiv_id":"2405.17486","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/eqmarl-entangled-quantum-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2405.17486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17486"}},"official":{"repos":["news-vt/eqmarl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/controlling-behavioral-diversity-in-multi","slug":"controlling-behavioral-diversity-in-multi","title":"Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning","date":"2024-05-23","arxiv_id":"2405.15054","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/controlling-behavioral-diversity-in-multi#ran","syntology_url":"https://syntology.ai/paper/2405.15054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15054"}},"official":{"repos":["proroklab/controllingbehavioraldiversity"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-multi-agent-reinforcement-learning","slug":"efficient-multi-agent-reinforcement-learning","title":"Efficient Multi-agent Reinforcement Learning by Planning","date":"2024-05-20","arxiv_id":"2405.11778","repositories_listed":1,"syntology":null},{"url":"/paper/a-distributed-approach-to-autonomous","slug":"a-distributed-approach-to-autonomous","title":"A Distributed Approach to Autonomous Intersection Management via Multi-Agent Reinforcement Learning","date":"2024-05-14","arxiv_id":"2405.08655","repositories_listed":1,"syntology":null},{"url":"/paper/modelling-opaque-bilateral-market-dynamics-in","slug":"modelling-opaque-bilateral-market-dynamics-in","title":"Modelling Opaque Bilateral Market Dynamics in Financial Trading: Insights from a Multi-Agent Simulation Study","date":"2024-05-05","arxiv_id":"2405.02849","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-cooperation-through-selective","slug":"enhancing-cooperation-through-selective","title":"Enhancing Cooperation through Selective Interaction and Long-term Experiences in Multi-Agent Reinforcement Learning","date":"2024-05-04","arxiv_id":"2405.02654","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-the-economic-impact-of-rationality","slug":"simulating-the-economic-impact-of-rationality","title":"Simulating the Economic Impact of Rationality through Reinforcement Learning and Agent-Based Modelling","date":"2024-05-03","arxiv_id":"2405.02161","repositories_listed":1,"syntology":null},{"url":"/paper/maexp-a-generic-platform-for-rl-based-multi","slug":"maexp-a-generic-platform-for-rl-based-multi","title":"MAexp: A Generic Platform for RL-based Multi-Agent Exploration","date":"2024-04-19","arxiv_id":"2404.12824","repositories_listed":1,"syntology":null},{"url":"/paper/group-aware-coordination-graph-for-multi","slug":"group-aware-coordination-graph-for-multi","title":"Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning","date":"2024-04-17","arxiv_id":"2404.10976","repositories_listed":1,"syntology":null},{"url":"/paper/towards-multi-agent-reinforcement-learning-3","slug":"towards-multi-agent-reinforcement-learning-3","title":"Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphs","date":"2024-04-17","arxiv_id":"2404.11014","repositories_listed":1,"syntology":null},{"url":"/paper/n-agent-ad-hoc-teamwork","slug":"n-agent-ad-hoc-teamwork","title":"N-Agent Ad Hoc Teamwork","date":"2024-04-16","arxiv_id":"2404.10740","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":5,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/n-agent-ad-hoc-teamwork#ran","syntology_url":"https://syntology.ai/paper/2404.10740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10740"}},"official":{"repos":["carolinewang01/naht"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/laser-learning-environment-a-new-environment","slug":"laser-learning-environment-a-new-environment","title":"Laser Learning Environment: A new environment for coordination-critical multi-agent tasks","date":"2024-04-04","arxiv_id":"2404.03596","repositories_listed":1,"syntology":null},{"url":"/paper/gov-rek-governed-reward-engineering-kernels","slug":"gov-rek-governed-reward-engineering-kernels","title":"GOV-REK: Governed Reward Engineering Kernels for Designing Robust Multi-Agent Reinforcement Learning Systems","date":"2024-04-01","arxiv_id":"2404.01131","repositories_listed":1,"syntology":null},{"url":"/paper/inferring-latent-temporal-sparse-coordination","slug":"inferring-latent-temporal-sparse-coordination","title":"Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning","date":"2024-03-28","arxiv_id":"2403.19253","repositories_listed":1,"syntology":null},{"url":"/paper/single-agent-actor-critic-for-decentralized","slug":"single-agent-actor-critic-for-decentralized","title":"Agent-Agnostic Centralized Training for Decentralized Multi-Agent Cooperative Driving","date":"2024-03-18","arxiv_id":"2403.11914","repositories_listed":1,"syntology":null},{"url":"/paper/ensembling-prioritized-hybrid-policies-for","slug":"ensembling-prioritized-hybrid-policies-for","title":"Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding","date":"2024-03-12","arxiv_id":"2403.07559","repositories_listed":1,"syntology":null},{"url":"/paper/generalising-multi-agent-cooperation-through","slug":"generalising-multi-agent-cooperation-through","title":"Generalising Multi-Agent Cooperation through Task-Agnostic Communication","date":"2024-03-11","arxiv_id":"2403.06750","repositories_listed":1,"syntology":null},{"url":"/paper/pps-qmix-periodically-parameter-sharing-for","slug":"pps-qmix-periodically-parameter-sharing-for","title":"PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning","date":"2024-03-05","arxiv_id":"2403.02635","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-episodic-memory-utilization-of","slug":"efficient-episodic-memory-utilization-of","title":"Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01112","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/efficient-episodic-memory-utilization-of#ran","syntology_url":"https://syntology.ai/paper/2403.01112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01112"}},"official":{"repos":["hyunghona/emu"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"c7d5ace162aa3fab3f8c5c44ea8afb2179003fa72bfde69d2b1683c8a0a7a755","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}