{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NA7RW4JRZIBYEUFZWPMRA5AOF2","short_pith_number":"pith:NA7RW4JR","schema_version":"1.0","canonical_sha256":"683f1b7131ca038250b9b3d910740e2e96dc5da3cf2a40f807554d829a17c682","source":{"kind":"arxiv","id":"1703.10069","version":4},"attestation_state":"computed","paper":{"title":"Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Haitao Long, Jun Wang, Peng Peng, Quan Yuan, Yaodong Yang, Ying Wen, Zhenkun Tang","submitted_at":"2017-03-29T14:37:25Z","abstract_excerpt":"Many artificial intelligence (AI) applications often require multiple intelligent agents to work in a collaborative effort. Efficient learning for intra-agent communication and coordination is an indispensable step towards general AI. In this paper, we take StarCraft combat game as a case study, where the task is to coordinate multiple agents as a team to defeat their enemies. To maintain a scalable yet effective communication protocol, we introduce a Multiagent Bidirectionally-Coordinated Network (BiCNet ['bIknet]) with a vectorised extension of actor-critic formulation. We show that BiCNet c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1703.10069","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-29T14:37:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aa888c7d1058677fb437a199a5e46cfdb52c2a23a1e754702cc9afddf6dc19d2","abstract_canon_sha256":"534ac0ca8d1aee7e1a2c3456c03e064e6bb35856dfe85913ca2600f619fa6d42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:10.598298Z","signature_b64":"/iQ6EaF3c8ed/pxbwCX04veaghEU8hu0CX3J56ujZPWtOqGuNs5D5HST6Cyzfn5MXIbVERPdTn+6S+IxvA6fAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"683f1b7131ca038250b9b3d910740e2e96dc5da3cf2a40f807554d829a17c682","last_reissued_at":"2026-05-18T00:35:10.597750Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:10.597750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Haitao Long, Jun Wang, Peng Peng, Quan Yuan, Yaodong Yang, Ying Wen, Zhenkun Tang","submitted_at":"2017-03-29T14:37:25Z","abstract_excerpt":"Many artificial intelligence (AI) applications often require multiple intelligent agents to work in a collaborative effort. Efficient learning for intra-agent communication and coordination is an indispensable step towards general AI. In this paper, we take StarCraft combat game as a case study, where the task is to coordinate multiple agents as a team to defeat their enemies. To maintain a scalable yet effective communication protocol, we introduce a Multiagent Bidirectionally-Coordinated Network (BiCNet ['bIknet]) with a vectorised extension of actor-critic formulation. We show that BiCNet c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10069","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1703.10069","created_at":"2026-05-18T00:35:10.597833+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.10069v4","created_at":"2026-05-18T00:35:10.597833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10069","created_at":"2026-05-18T00:35:10.597833+00:00"},{"alias_kind":"pith_short_12","alias_value":"NA7RW4JRZIBY","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"NA7RW4JRZIBYEUFZ","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"NA7RW4JR","created_at":"2026-05-18T12:31:31.346846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.09466","citing_title":"An Actor-Critic-Attention Mechanism for Deep Reinforcement Learning in Multi-view Environments","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03785","citing_title":"Decomposing Communication Gain and Delay Cost Under Cross-Timestep Delays in Cooperative Multi-Agent Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08728","citing_title":"Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NA7RW4JRZIBYEUFZWPMRA5AOF2","json":"https://pith.science/pith/NA7RW4JRZIBYEUFZWPMRA5AOF2.json","graph_json":"https://pith.science/api/pith-number/NA7RW4JRZIBYEUFZWPMRA5AOF2/graph.json","events_json":"https://pith.science/api/pith-number/NA7RW4JRZIBYEUFZWPMRA5AOF2/events.json","paper":"https://pith.science/paper/NA7RW4JR"},"agent_actions":{"view_html":"https://pith.science/pith/NA7RW4JRZIBYEUFZWPMRA5AOF2","download_json":"https://pith.science/pith/NA7RW4JRZIBYEUFZWPMRA5AOF2.json","view_paper":"https://pith.science/paper/NA7RW4JR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.10069&json=true","fetch_graph":"https://pith.science/api/pith-number/NA7RW4JRZIBYEUFZWPMRA5AOF2/graph.json","fetch_events":"https://pith.science/api/pith-number/NA7RW4JRZIBYEUFZWPMRA5AOF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NA7RW4JRZIBYEUFZWPMRA5AOF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NA7RW4JRZIBYEUFZWPMRA5AOF2/action/storage_attestation","attest_author":"https://pith.science/pith/NA7RW4JRZIBYEUFZWPMRA5AOF2/action/author_attestation","sign_citation":"https://pith.science/pith/NA7RW4JRZIBYEUFZWPMRA5AOF2/action/citation_signature","submit_replication":"https://pith.science/pith/NA7RW4JRZIBYEUFZWPMRA5AOF2/action/replication_record"}},"created_at":"2026-05-18T00:35:10.597833+00:00","updated_at":"2026-05-18T00:35:10.597833+00:00"}