{"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/smac","name":"SMAC","slug":"smac","description_markdown":"The StarCraft Multi-Agent Challenge (SMAC) is a benchmark that provides elements of partial observability, challenging dynamics, and high-dimensional observation spaces. SMAC is built using the StarCraft II game engine, creating a testbed for research in cooperative MARL where each game unit is an independent RL agent.","categories":[{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":121,"papers_with_code":54,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/smac-on-smac-6h-vs-8z-1","slug":"smac-on-smac-6h-vs-8z-1","dataset":"SMAC 6h_vs_8z","dataset_url":"/dataset/smac","rows_in_archive":14,"metrics":["Median Win Rate","Average Score"],"first_row_in_archive_order":{"model":"ACE","paper_title":"ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency","paper_url":"/paper/ace-cooperative-multi-agent-q-learning-with","paper_date":"2022-11-29","arxiv_id":"2211.16068","code_links":[{"title":"opendilab/ace","url":"https://github.com/opendilab/ace"}],"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ace-cooperative-multi-agent-q-learning-with#ran","syntology_url":"https://syntology.ai/paper/2211.16068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16068"}},"official":{"repos":["opendilab/ace"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/smac-on-smac-mmm2-1","slug":"smac-on-smac-mmm2-1","dataset":"SMAC MMM2","dataset_url":"/dataset/smac","rows_in_archive":14,"metrics":["Median Win Rate","Average Score"],"first_row_in_archive_order":{"model":"ACE","paper_title":"ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency","paper_url":"/paper/ace-cooperative-multi-agent-q-learning-with","paper_date":"2022-11-29","arxiv_id":"2211.16068","code_links":[{"title":"opendilab/ace","url":"https://github.com/opendilab/ace"}],"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ace-cooperative-multi-agent-q-learning-with#ran","syntology_url":"https://syntology.ai/paper/2211.16068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16068"}},"official":{"repos":["opendilab/ace"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/smac-on-smac-3s5z-vs-3s6z-1","slug":"smac-on-smac-3s5z-vs-3s6z-1","dataset":"SMAC 3s5z_vs_3s6z","dataset_url":"/dataset/smac","rows_in_archive":13,"metrics":["Median Win Rate","Average Score"],"first_row_in_archive_order":{"model":"ACE","paper_title":"ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency","paper_url":"/paper/ace-cooperative-multi-agent-q-learning-with","paper_date":"2022-11-29","arxiv_id":"2211.16068","code_links":[{"title":"opendilab/ace","url":"https://github.com/opendilab/ace"}],"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ace-cooperative-multi-agent-q-learning-with#ran","syntology_url":"https://syntology.ai/paper/2211.16068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16068"}},"official":{"repos":["opendilab/ace"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/smac-on-smac-corridor","slug":"smac-on-smac-corridor","dataset":"SMAC corridor","dataset_url":"/dataset/smac","rows_in_archive":13,"metrics":["Median Win Rate","Average Score"],"first_row_in_archive_order":{"model":"ACE","paper_title":"ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency","paper_url":"/paper/ace-cooperative-multi-agent-q-learning-with","paper_date":"2022-11-29","arxiv_id":"2211.16068","code_links":[{"title":"opendilab/ace","url":"https://github.com/opendilab/ace"}],"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ace-cooperative-multi-agent-q-learning-with#ran","syntology_url":"https://syntology.ai/paper/2211.16068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16068"}},"official":{"repos":["opendilab/ace"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/smac-on-smac-27m-vs-30m","slug":"smac-on-smac-27m-vs-30m","dataset":"SMAC 27m_vs_30m","dataset_url":"/dataset/smac","rows_in_archive":11,"metrics":["Median Win Rate","Average Score"],"first_row_in_archive_order":{"model":"DDN","paper_title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","paper_url":"/paper/dfac-framework-factorizing-the-value-function","paper_date":"2021-02-16","arxiv_id":"2102.07936","code_links":[{"title":"j3soon/dfac","url":"https://github.com/j3soon/dfac"}],"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":0,"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/dfac-framework-factorizing-the-value-function#ran","syntology_url":"https://syntology.ai/paper/2102.07936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07936"}},"official":{"repos":["j3soon/dfac"],"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"]}}}},{"leaderboard":"/sota/smac-on-smac-26m-vs-30m","slug":"smac-on-smac-26m-vs-30m","dataset":"SMAC 26m_vs_30m","dataset_url":null,"rows_in_archive":6,"metrics":["Average Score","Median Win Rate"],"first_row_in_archive_order":{"model":"DMIX","paper_title":"A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning","paper_url":"/paper/a-unified-framework-for-factorizing","paper_date":"2023-06-04","arxiv_id":"2306.02430","code_links":[{"title":"j3soon/dfac-extended","url":"https://github.com/j3soon/dfac-extended"}],"syntology":null}},{"leaderboard":"/sota/smac-on-smac-3s5z-vs-4s6z","slug":"smac-on-smac-3s5z-vs-4s6z","dataset":"SMAC 3s5z_vs_4s6z","dataset_url":null,"rows_in_archive":6,"metrics":["Average Score","Median Win Rate"],"first_row_in_archive_order":{"model":"DDN","paper_title":"A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning","paper_url":"/paper/a-unified-framework-for-factorizing","paper_date":"2023-06-04","arxiv_id":"2306.02430","code_links":[{"title":"j3soon/dfac-extended","url":"https://github.com/j3soon/dfac-extended"}],"syntology":null}},{"leaderboard":"/sota/smac-on-smac-6h-vs-9z","slug":"smac-on-smac-6h-vs-9z","dataset":"SMAC 6h_vs_9z","dataset_url":null,"rows_in_archive":6,"metrics":["Average Score","Median Win Rate"],"first_row_in_archive_order":{"model":"DDN","paper_title":"A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning","paper_url":"/paper/a-unified-framework-for-factorizing","paper_date":"2023-06-04","arxiv_id":"2306.02430","code_links":[{"title":"j3soon/dfac-extended","url":"https://github.com/j3soon/dfac-extended"}],"syntology":null}},{"leaderboard":"/sota/smac-on-smac-corridor-2z-vs-24zg","slug":"smac-on-smac-corridor-2z-vs-24zg","dataset":"SMAC corridor_2z_vs_24zg","dataset_url":null,"rows_in_archive":6,"metrics":["Average Score","Median Win Rate"],"first_row_in_archive_order":{"model":"DDN","paper_title":"A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning","paper_url":"/paper/a-unified-framework-for-factorizing","paper_date":"2023-06-04","arxiv_id":"2306.02430","code_links":[{"title":"j3soon/dfac-extended","url":"https://github.com/j3soon/dfac-extended"}],"syntology":null}},{"leaderboard":"/sota/smac-on-smac-mmm2-7m2m1m-vs-8m4m1m","slug":"smac-on-smac-mmm2-7m2m1m-vs-8m4m1m","dataset":"SMAC MMM2_7m2M1M_vs_8m4M1M","dataset_url":null,"rows_in_archive":6,"metrics":["Average Score","Median Win Rate"],"first_row_in_archive_order":{"model":"DDN","paper_title":"A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning","paper_url":"/paper/a-unified-framework-for-factorizing","paper_date":"2023-06-04","arxiv_id":"2306.02430","code_links":[{"title":"j3soon/dfac-extended","url":"https://github.com/j3soon/dfac-extended"}],"syntology":null}},{"leaderboard":"/sota/smac-on-smac-mmm2-7m2m1m-vs-9m3m1m","slug":"smac-on-smac-mmm2-7m2m1m-vs-9m3m1m","dataset":"SMAC MMM2_7m2M1M_vs_9m3M1M","dataset_url":null,"rows_in_archive":6,"metrics":["Average Score","Median Win Rate"],"first_row_in_archive_order":{"model":"DDN","paper_title":"A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning","paper_url":"/paper/a-unified-framework-for-factorizing","paper_date":"2023-06-04","arxiv_id":"2306.02430","code_links":[{"title":"j3soon/dfac-extended","url":"https://github.com/j3soon/dfac-extended"}],"syntology":null}}],"datasets":[{"url":"/dataset/smac","name":"SMAC","full_name":"The StarCraft Multi-Agent Challenge","num_papers_in_archive":324}],"subtasks":[{"url":"/task/smac-1","name":"SMAC+"},{"url":"/task/smac-plus","name":"SMAC Plus"}],"parent_tasks":[{"url":"/task/multi-agent-reinforcement-learning","name":"Multi-agent Reinforcement Learning"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":121,"of_with_code":54,"tagged_in_all":121,"counts":{"archive_papers_tagged":121,"with_a_code_link":54,"where_syntology_ran_a_sample":13,"not_listed_spam_title":0,"listed":121,"listed_where_code_ran":13,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":2,"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"},"items":[{"url":"/paper/the-starcraft-multi-agent-challenge","slug":"the-starcraft-multi-agent-challenge","title":"The StarCraft Multi-Agent Challenge","date":"2019-02-11","arxiv_id":"1902.04043","repositories_listed":23,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":14,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-starcraft-multi-agent-challenge#ran","syntology_url":"https://syntology.ai/paper/1902.04043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.04043"}},"official":{"repos":["oxwhirl/pymarl","oxwhirl/smac"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/is-independent-learning-all-you-need-in-the","slug":"is-independent-learning-all-you-need-in-the","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","date":"2020-11-18","arxiv_id":"2011.09533","repositories_listed":7,"syntology":null},{"url":"/paper/maven-multi-agent-variational-exploration","slug":"maven-multi-agent-variational-exploration","title":"MAVEN: Multi-Agent Variational Exploration","date":"2019-10-16","arxiv_id":"1910.07483","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/maven-multi-agent-variational-exploration#ran","syntology_url":"https://syntology.ai/paper/1910.07483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.07483"}},"official":{"repos":["AnujMahajanOxf/MAVEN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mlrmbo-a-modular-framework-for-model-based","slug":"mlrmbo-a-modular-framework-for-model-based","title":"mlrMBO: A Modular Framework for Model-Based Optimization of Expensive Black-Box Functions","date":"2017-03-09","arxiv_id":"1703.03373","repositories_listed":4,"syntology":null},{"url":"/paper/deep-multi-agent-reinforcement-learning-for","slug":"deep-multi-agent-reinforcement-learning-for","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","date":"2020-03-14","arxiv_id":"2003.06709","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-multi-agent-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.06709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06709"}},"official":{"repos":["schroederdewitt/multiagent_mujoco"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperparameter-tricks-in-multi-agent","slug":"hyperparameter-tricks-in-multi-agent","title":"Rethinking the Implementation Matters in Cooperative Multi-Agent Reinforcement Learning","date":"2021-02-06","arxiv_id":"2102.03479","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hyperparameter-tricks-in-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2102.03479","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03479"}},"official":{"repos":["hijkzzz/pymarl2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/generalizable-agent-modeling-for-agent","slug":"generalizable-agent-modeling-for-agent","title":"Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation","date":"2025-06-20","arxiv_id":"2506.16718","repositories_listed":1,"syntology":null},{"url":"/paper/curriculum-learning-with-counterfactual-group","slug":"curriculum-learning-with-counterfactual-group","title":"Curriculum Learning With Counterfactual Group Relative Policy Advantage For Multi-Agent Reinforcement Learning","date":"2025-06-09","arxiv_id":"2506.07548","repositories_listed":1,"syntology":null},{"url":"/paper/jaxrobotarium-training-and-deploying-multi","slug":"jaxrobotarium-training-and-deploying-multi","title":"JaxRobotarium: Training and Deploying Multi-Robot Policies in 10 Minutes","date":"2025-05-10","arxiv_id":"2505.06771","repositories_listed":1,"syntology":null},{"url":"/paper/learning-generalizable-skills-from-offline","slug":"learning-generalizable-skills-from-offline","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","date":"2025-03-27","arxiv_id":"2503.21200","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/learning-generalizable-skills-from-offline#ran","syntology_url":"https://syntology.ai/paper/2503.21200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21200"}},"official":{"repos":["mooricAnna/HiSSD"],"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/vlms-play-starcraft-ii-a-benchmark-and","slug":"vlms-play-starcraft-ii-a-benchmark-and","title":"AVA: Attentive VLM Agent for Mastering StarCraft II","date":"2025-03-07","arxiv_id":"2503.05383","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/dual-ensembled-multiagent-q-learning-with","slug":"dual-ensembled-multiagent-q-learning-with","title":"Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer","date":"2025-02-04","arxiv_id":"2502.02018","repositories_listed":1,"syntology":null},{"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/llm-pysc2-starcraft-ii-learning-environment","slug":"llm-pysc2-starcraft-ii-learning-environment","title":"LLM-PySC2: Starcraft II learning environment for Large Language Models","date":"2024-11-08","arxiv_id":"2411.05348","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/choices-are-more-important-than-efforts-llm","slug":"choices-are-more-important-than-efforts-llm","title":"Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration","date":"2024-10-03","arxiv_id":"2410.02511","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/choices-are-more-important-than-efforts-llm#ran","syntology_url":"https://syntology.ai/paper/2410.02511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02511"}},"official":{"repos":["hijkzzz/pymarl2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/decentralized-transformers-with-centralized","slug":"decentralized-transformers-with-centralized","title":"Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models","date":"2024-06-22","arxiv_id":"2406.15836","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/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/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/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/fox-formation-aware-exploration-in-multi","slug":"fox-formation-aware-exploration-in-multi","title":"FoX: Formation-aware exploration in multi-agent reinforcement learning","date":"2023-08-22","arxiv_id":"2308.11272","repositories_listed":1,"syntology":null},{"url":"/paper/homopt-a-homotopy-based-hyperparameter","slug":"homopt-a-homotopy-based-hyperparameter","title":"HomOpt: A Homotopy-Based Hyperparameter Optimization Method","date":"2023-08-07","arxiv_id":"2308.03317","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-framework-for-factorizing","slug":"a-unified-framework-for-factorizing","title":"A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning","date":"2023-06-04","arxiv_id":"2306.02430","repositories_listed":1,"syntology":null},{"url":"/paper/robust-multi-agent-coordination-via","slug":"robust-multi-agent-coordination-via","title":"Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers","date":"2023-05-10","arxiv_id":"2305.05909","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/robust-multi-agent-coordination-via#ran","syntology_url":"https://syntology.ai/paper/2305.05909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05909"}},"official":{"repos":["zzq-bot/romance"],"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/smaclite-a-lightweight-environment-for-multi","slug":"smaclite-a-lightweight-environment-for-multi","title":"SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning","date":"2023-05-09","arxiv_id":"2305.05566","repositories_listed":1,"syntology":null},{"url":"/paper/ghq-grouped-hybrid-q-learning-for","slug":"ghq-grouped-hybrid-q-learning-for","title":"GHQ: Grouped Hybrid Q Learning for Heterogeneous Cooperative Multi-agent Reinforcement Learning","date":"2023-03-02","arxiv_id":"2303.01070","repositories_listed":1,"syntology":null},{"url":"/paper/attacking-cooperative-multi-agent","slug":"attacking-cooperative-multi-agent","title":"Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence","date":"2023-02-07","arxiv_id":"2302.03322","repositories_listed":1,"syntology":null},{"url":"/paper/self-motivated-multi-agent-exploration","slug":"self-motivated-multi-agent-exploration","title":"Self-Motivated Multi-Agent Exploration","date":"2023-01-05","arxiv_id":"2301.02083","repositories_listed":1,"syntology":null},{"url":"/paper/smacv2-an-improved-benchmark-for-cooperative-1","slug":"smacv2-an-improved-benchmark-for-cooperative-1","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","date":"2022-12-14","arxiv_id":"2212.07489","repositories_listed":1,"syntology":null},{"url":"/paper/effects-of-spectral-normalization-in-multi","slug":"effects-of-spectral-normalization-in-multi","title":"Effects of Spectral Normalization in Multi-agent Reinforcement Learning","date":"2022-12-10","arxiv_id":"2212.05331","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/effects-of-spectral-normalization-in-multi#ran","syntology_url":"https://syntology.ai/paper/2212.05331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05331"}},"official":{"repos":["kinalmehta/epymarl_spectral"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ace-cooperative-multi-agent-q-learning-with","slug":"ace-cooperative-multi-agent-q-learning-with","title":"ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency","date":"2022-11-29","arxiv_id":"2211.16068","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ace-cooperative-multi-agent-q-learning-with#ran","syntology_url":"https://syntology.ai/paper/2211.16068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16068"}},"official":{"repos":["opendilab/ace"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-identity-aware-learning-for-multi","slug":"contrastive-identity-aware-learning-for-multi","title":"Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition","date":"2022-11-23","arxiv_id":"2211.12712","repositories_listed":1,"syntology":null},{"url":"/paper/decision-making-with-imaginary-opponent","slug":"decision-making-with-imaginary-opponent","title":"Decision-making with Speculative Opponent Models","date":"2022-11-22","arxiv_id":"2211.11940","repositories_listed":1,"syntology":null},{"url":"/paper/latent-state-marginalization-as-a-low-cost","slug":"latent-state-marginalization-as-a-low-cost","title":"Latent State Marginalization as a Low-cost Approach for Improving Exploration","date":"2022-10-03","arxiv_id":"2210.00999","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/latent-state-marginalization-as-a-low-cost#ran","syntology_url":"https://syntology.ai/paper/2210.00999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.00999"}},"official":{"repos":["zdhnarsil/stochastic-marginal-actor-critic"],"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":["community","official"]}}},{"url":"/paper/transformer-based-value-function","slug":"transformer-based-value-function","title":"Transformer-based Value Function Decomposition for Cooperative Multi-agent Reinforcement Learning in StarCraft","date":"2022-08-15","arxiv_id":"2208.07298","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-multi-agent-model-based","slug":"scalable-multi-agent-model-based","title":"Scalable Multi-Agent Model-Based Reinforcement Learning","date":"2022-05-25","arxiv_id":"2205.15023","repositories_listed":1,"syntology":null},{"url":"/paper/value-function-factorisation-with-hypergraph","slug":"value-function-factorisation-with-hypergraph","title":"Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution","date":"2021-12-09","arxiv_id":"2112.06771","repositories_listed":1,"syntology":null},{"url":"/paper/offline-pre-trained-multi-agent-decision-1","slug":"offline-pre-trained-multi-agent-decision-1","title":"Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks","date":"2021-12-06","arxiv_id":"2112.02845","repositories_listed":1,"syntology":null},{"url":"/paper/shaq-incorporating-shapley-value-theory-into","slug":"shaq-incorporating-shapley-value-theory-into","title":"SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning","date":"2021-05-31","arxiv_id":"2105.15013","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/shaq-incorporating-shapley-value-theory-into#ran","syntology_url":"https://syntology.ai/paper/2105.15013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.15013"}},"official":{"repos":["hsvgbkhgbv/shapley-q-learning"],"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/dfac-framework-factorizing-the-value-function","slug":"dfac-framework-factorizing-the-value-function","title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","date":"2021-02-16","arxiv_id":"2102.07936","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":0,"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/dfac-framework-factorizing-the-value-function#ran","syntology_url":"https://syntology.ai/paper/2102.07936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07936"}},"official":{"repos":["j3soon/dfac"],"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/updet-universal-multi-agent-reinforcement","slug":"updet-universal-multi-agent-reinforcement","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","date":"2021-01-20","arxiv_id":"2101.08001","repositories_listed":1,"syntology":null},{"url":"/paper/qvmix-and-qvmix-max-extending-the-deep","slug":"qvmix-and-qvmix-max-extending-the-deep","title":"QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning","date":"2020-12-22","arxiv_id":"2012.12062","repositories_listed":1,"syntology":null},{"url":"/paper/autoweka4mcps-avatar-accelerating-automated","slug":"autoweka4mcps-avatar-accelerating-automated","title":"AutoWeka4MCPS-AVATAR: Accelerating Automated Machine Learning Pipeline Composition and Optimisation","date":"2020-11-21","arxiv_id":"2011.11846","repositories_listed":1,"syntology":null},{"url":"/paper/graph-convolutional-value-decomposition-in-1","slug":"graph-convolutional-value-decomposition-in-1","title":"Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning","date":"2020-10-09","arxiv_id":"2010.04740","repositories_listed":1,"syntology":null},{"url":"/paper/additive-tree-structured-conditional","slug":"additive-tree-structured-conditional","title":"Additive Tree-Structured Conditional Parameter Spaces in Bayesian Optimization: A Novel Covariance Function and a Fast Implementation","date":"2020-10-06","arxiv_id":"2010.03171","repositories_listed":1,"syntology":null},{"url":"/paper/deep-implicit-coordination-graphs-for-multi","slug":"deep-implicit-coordination-graphs-for-multi","title":"Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning","date":"2020-06-19","arxiv_id":"2006.11438","repositories_listed":1,"syntology":null},{"url":"/paper/monotonic-value-function-factorisation-for","slug":"monotonic-value-function-factorisation-for","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","date":"2020-03-19","arxiv_id":"2003.08839","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":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) · 0 unverified","sample_list":"/paper/monotonic-value-function-factorisation-for#ran","syntology_url":"https://syntology.ai/paper/2003.08839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.08839"}},"official":{"repos":["oxwhirl/pymarl"],"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/smix-enhancing-centralized-value-functions","slug":"smix-enhancing-centralized-value-functions","title":"SMIX($λ$): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning","date":"2019-11-11","arxiv_id":"1911.04094","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-performance-of-differential-evolution","slug":"on-the-performance-of-differential-evolution","title":"On the Performance of Differential Evolution for Hyperparameter Tuning","date":"2019-04-15","arxiv_id":"1904.06960","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-evolutionary-methods-for-game-agent","slug":"efficient-evolutionary-methods-for-game-agent","title":"Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best","date":"2019-01-03","arxiv_id":"1901.00723","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-hyperparameter-optimization-of-deep","slug":"efficient-hyperparameter-optimization-of-deep","title":"Efficient Hyperparameter Optimization of Deep Learning Algorithms Using Deterministic RBF Surrogates","date":"2016-07-28","arxiv_id":"1607.08316","repositories_listed":1,"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":"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":"pocaii-parameter-optimization-with-conscious","title":"POCAII: Parameter Optimization with Conscious Allocation using Iterative Intelligence","date":"2025-05-16","arxiv_id":"2505.11745","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":"low-rank-agent-specific-adaptation-lorasa-for","title":"Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning","date":"2025-02-08","arxiv_id":"2502.05573","repositories_listed":0,"syntology":null},{"url":null,"slug":"o-mapl-offline-multi-agent-preference","title":"O-MAPL: Offline Multi-agent Preference Learning","date":"2025-01-31","arxiv_id":"2501.18944","repositories_listed":0,"syntology":null},{"url":null,"slug":"blast-a-stealthy-backdoor-leverage-attack","title":"BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems","date":"2025-01-03","arxiv_id":"2501.01593","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-to-online-multi-agent-reinforcement","title":"Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration","date":"2024-10-25","arxiv_id":"2410.19450","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-safety-modulator-actor-critic-method-in","title":"A Safety Modulator Actor-Critic Method in Model-Free Safe Reinforcement Learning and Application in UAV Hovering","date":"2024-10-09","arxiv_id":"2410.06847","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-spatiotemporal-stealthy-backdoor-attack","title":"A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning","date":"2024-09-12","arxiv_id":"2409.07775","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-based-episodes-augmentation-for","title":"Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning","date":"2024-08-23","arxiv_id":"2408.13092","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-global-parameter-sharing-in","title":"Improving Global Parameter-sharing in Physically Heterogeneous Multi-agent Reinforcement Learning with Unified Action Space","date":"2024-08-14","arxiv_id":"2408.07395","repositories_listed":0,"syntology":null},{"url":null,"slug":"cuda2-an-approach-for-incorporating-traitor","title":"CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems","date":"2024-06-25","arxiv_id":"2406.17425","repositories_listed":0,"syntology":null},{"url":null,"slug":"higher-replay-ratio-empowers-sample-efficient","title":"Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning","date":"2024-04-15","arxiv_id":"2404.09715","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-multi-agent-reinforcement-2","title":"Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration","date":"2024-04-05","arxiv_id":"2404.03869","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-understandings-and-configurations-in","title":"Better Understandings and Configurations in MaxSAT Local Search Solvers via Anytime Performance Analysis","date":"2024-03-11","arxiv_id":"2403.06568","repositories_listed":0,"syntology":null},{"url":null,"slug":"imagine-initialize-and-explore-an-effective","title":"Imagine, Initialize, and Explore: An Effective Exploration Method in Multi-Agent Reinforcement Learning","date":"2024-02-28","arxiv_id":"2402.17978","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-individual-and-collective-objectives","title":"Aligning Individual and Collective Objectives in Multi-Agent Cooperation","date":"2024-02-19","arxiv_id":"2402.12416","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-multi-agent-transfer-reinforcement","title":"Enabling Multi-Agent Transfer Reinforcement Learning via Scenario Independent Representation","date":"2024-02-13","arxiv_id":"2402.08184","repositories_listed":0,"syntology":null},{"url":null,"slug":"maidcrl-semi-centralized-multi-agent","title":"MAIDCRL: Semi-centralized Multi-Agent Influence Dense-CNN Reinforcement Learning","date":"2024-02-12","arxiv_id":"2402.07890","repositories_listed":0,"syntology":null},{"url":null,"slug":"poisson-process-for-bayesian-optimization","title":"Poisson Process for Bayesian Optimization","date":"2024-02-05","arxiv_id":"2402.02687","repositories_listed":0,"syntology":null},{"url":null,"slug":"t2mac-targeted-and-trusted-multi-agent","title":"T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration","date":"2024-01-19","arxiv_id":"2401.10973","repositories_listed":0,"syntology":null},{"url":null,"slug":"agentmixer-multi-agent-correlated-policy","title":"AgentMixer: Multi-Agent Correlated Policy Factorization","date":"2024-01-16","arxiv_id":"2401.08728","repositories_listed":0,"syntology":null},{"url":null,"slug":"innate-values-driven-reinforcement-learning","title":"Innate-Values-driven Reinforcement Learning based Cooperative Multi-Agent Cognitive Modeling","date":"2024-01-10","arxiv_id":"2401.05572","repositories_listed":0,"syntology":null},{"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":"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":"masked-pretraining-for-multi-agent-decision","title":"MaskMA: Towards Zero-Shot Multi-Agent Decision Making with Mask-Based Collaborative Learning","date":"2023-10-18","arxiv_id":"2310.11846","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":"research-on-multi-agent-communication-and","title":"Research on Multi-Agent Communication and Collaborative Decision-Making Based on Deep Reinforcement Learning","date":"2023-05-23","arxiv_id":"2305.17141","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-level-latent-variable-model-for-sample","title":"MABL: Bi-Level Latent-Variable World Model for Sample-Efficient Multi-Agent Reinforcement Learning","date":"2023-04-12","arxiv_id":"2304.06011","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-classification-of-pre-defined","title":"Automated classification of pre-defined movement patterns: A comparison between GNSS and UWB technology","date":"2023-03-10","arxiv_id":"2303.07107","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-transformer-for-offline-meta","title":"Contextual Transformer for Offline Meta Reinforcement Learning","date":"2022-11-15","arxiv_id":"2211.08016","repositories_listed":0,"syntology":null},{"url":null,"slug":"ptde-personalized-training-with-distillated","title":"PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning","date":"2022-10-17","arxiv_id":"2210.08872","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-correntropy-value-decomposition-for","title":"Maximum Correntropy Value Decomposition for Multi-agent Deep Reinforcemen Learning","date":"2022-08-07","arxiv_id":"2208.03663","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-diagnosis-via-measuring-role-diversity","title":"Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL","date":"2022-06-01","arxiv_id":"2207.05683","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-distributed-framework-for","title":"Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning","date":"2022-05-11","arxiv_id":"2205.05248","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-comprehensive-testing-on-the","title":"Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning","date":"2022-04-17","arxiv_id":"2204.07932","repositories_listed":0,"syntology":null},{"url":null,"slug":"api-boosting-multi-agent-reinforcement","title":"Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework","date":"2022-03-10","arxiv_id":"2203.05285","repositories_listed":0,"syntology":null},{"url":null,"slug":"depthwise-convolution-for-multi-agent","title":"Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation","date":"2022-03-06","arxiv_id":"2203.02896","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-semantic-epsilon-greedy","title":"Exploiting Semantic Epsilon Greedy Exploration Strategy in Multi-Agent Reinforcement Learning","date":"2022-01-26","arxiv_id":"2201.10803","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-hyper-parameter","title":"A Comparative study of Hyper-Parameter Optimization Tools","date":"2022-01-17","arxiv_id":"2201.06433","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-advantage-networks-for-cooperative","title":"Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning","date":"2021-12-23","arxiv_id":"2112.12458","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-based-episodic-memory-for-multi-agent","title":"State-based Episodic Memory for Multi-Agent Reinforcement Learning","date":"2021-10-19","arxiv_id":"2110.09817","repositories_listed":0,"syntology":null},{"url":null,"slug":"marnet-backdoor-attacks-against-value","title":"MARNET: Backdoor Attacks against Value-Decomposition Multi-Agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-the-monotonicity-constraint-in","title":"Revisiting the Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"role-diversity-matters-a-study-of-cooperative","title":"Role Diversity Matters: A Study of Cooperative Training Strategies for Multi-Agent RL","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":14,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/smac-on-smac-mmm2-1","since_archive":"/sota/smac-on-smac-mmm2-1#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/smac-on-smac-3s5z-vs-3s6z-1","since_archive":"/sota/smac-on-smac-3s5z-vs-3s6z-1#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":13,"papers_where_code_ran_first_page":"/task/smac/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/smac/papers/2","json":"/task/smac/papers/2.json","rows":21},{"order":"ran","page":1,"of":1,"url":"/task/smac/papers/ran/1","json":"/task/smac/papers/ran/1.json","rows":13}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"7628a204813d4b49d2c5b8809559d54dc3ed160f572ffe9f637fd298d0a357c7","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}