{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/multiagent-bidirectionally-coordinated-nets","title":"Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games","arxiv_id":"1703.10069","date":"2017-03-29","proceeding":null,"authors":["Peng Peng","Ying Wen","Yaodong Yang","Quan Yuan","Zhenkun Tang","Haitao Long","Jun Wang"],"abstract":"Many artificial intelligence (AI) applications often require multiple\nintelligent agents to work in a collaborative effort. Efficient learning for\nintra-agent communication and coordination is an indispensable step towards\ngeneral AI. In this paper, we take StarCraft combat game as a case study, where\nthe task is to coordinate multiple agents as a team to defeat their enemies. To\nmaintain a scalable yet effective communication protocol, we introduce a\nMultiagent Bidirectionally-Coordinated Network (BiCNet ['bIknet]) with a\nvectorised extension of actor-critic formulation. We show that BiCNet can\nhandle different types of combats with arbitrary numbers of AI agents for both\nsides. Our analysis demonstrates that without any supervisions such as human\ndemonstrations or labelled data, BiCNet could learn various types of advanced\ncoordination strategies that have been commonly used by experienced game\nplayers. In our experiments, we evaluate our approach against multiple\nbaselines under different scenarios; it shows state-of-the-art performance, and\npossesses potential values for large-scale real-world applications.","url_abs":"http://arxiv.org/abs/1703.10069v4","url_pdf":"http://arxiv.org/pdf/1703.10069v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multiagent-bidirectionally-coordinated-nets","repo_url":"https://github.com/Coac/CommNet-BiCnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"multiagent-bidirectionally-coordinated-nets","repo_url":"https://github.com/isp1tze/MAProj","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"starcraft","task_name":"Starcraft"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.10069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.10069"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/isp1tze/MAProj","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Coac/CommNet-BiCnet","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"dd2a584641f0de0e","entry":"parse_arg","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"dd2a584641f0de0e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}