{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:C4K53QOIWLP7Z236TW2TOINSS2","short_pith_number":"pith:C4K53QOI","schema_version":"1.0","canonical_sha256":"1715ddc1c8b2dffceb7e9db53721b296850d4c3dded04c1d25dfcf17cd83aa01","source":{"kind":"arxiv","id":"1909.04224","version":2},"attestation_state":"computed","paper":{"title":"Signal Instructed Coordination in Cooperative Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Fei Fang, Haifeng Zhang, Hongyi Guo, Liheng Chen, Ming Zhou, Qing Wang, Weinan Zhang, Yali Du, Yaoming Zhu, Yong Yu","submitted_at":"2019-09-10T01:28:25Z","abstract_excerpt":"In many real-world problems, a team of agents need to collaborate to maximize the common reward. Although existing works formulate this problem into a centralized learning with decentralized execution framework, which avoids the non-stationary problem in training, their decentralized execution paradigm limits the agents' capability to coordinate. Inspired by the concept of correlated equilibrium, we propose to introduce a coordination signal to address this limitation, and theoretically show that following mild conditions, decentralized agents with the coordination signal can coordinate their "},"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":"1909.04224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-09-10T01:28:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8def429917f1d96dabcda20af6812b1c87148a6f2a70a81d7bb6e5bb31229a2f","abstract_canon_sha256":"ab7afb0c8cfa658b2138a85a425e3f4d9c9648a7485df54efa425f2a7c8c9be0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:44.121546Z","signature_b64":"WypMl7dpiyxx7EzetjTgql4BFQ0vNr2ub0irvXIk3PdN3M9mdw00+VCFfgoTNswTDjvfc4EvebIFIl1DhniPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1715ddc1c8b2dffceb7e9db53721b296850d4c3dded04c1d25dfcf17cd83aa01","last_reissued_at":"2026-07-05T00:20:44.121058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:44.121058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Signal Instructed Coordination in Cooperative Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Fei Fang, Haifeng Zhang, Hongyi Guo, Liheng Chen, Ming Zhou, Qing Wang, Weinan Zhang, Yali Du, Yaoming Zhu, Yong Yu","submitted_at":"2019-09-10T01:28:25Z","abstract_excerpt":"In many real-world problems, a team of agents need to collaborate to maximize the common reward. Although existing works formulate this problem into a centralized learning with decentralized execution framework, which avoids the non-stationary problem in training, their decentralized execution paradigm limits the agents' capability to coordinate. Inspired by the concept of correlated equilibrium, we propose to introduce a coordination signal to address this limitation, and theoretically show that following mild conditions, decentralized agents with the coordination signal can coordinate their "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04224","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.04224/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1909.04224","created_at":"2026-07-05T00:20:44.121112+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.04224v2","created_at":"2026-07-05T00:20:44.121112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04224","created_at":"2026-07-05T00:20:44.121112+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4K53QOIWLP7","created_at":"2026-07-05T00:20:44.121112+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4K53QOIWLP7Z236","created_at":"2026-07-05T00:20:44.121112+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4K53QOI","created_at":"2026-07-05T00:20:44.121112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C4K53QOIWLP7Z236TW2TOINSS2","json":"https://pith.science/pith/C4K53QOIWLP7Z236TW2TOINSS2.json","graph_json":"https://pith.science/api/pith-number/C4K53QOIWLP7Z236TW2TOINSS2/graph.json","events_json":"https://pith.science/api/pith-number/C4K53QOIWLP7Z236TW2TOINSS2/events.json","paper":"https://pith.science/paper/C4K53QOI"},"agent_actions":{"view_html":"https://pith.science/pith/C4K53QOIWLP7Z236TW2TOINSS2","download_json":"https://pith.science/pith/C4K53QOIWLP7Z236TW2TOINSS2.json","view_paper":"https://pith.science/paper/C4K53QOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.04224&json=true","fetch_graph":"https://pith.science/api/pith-number/C4K53QOIWLP7Z236TW2TOINSS2/graph.json","fetch_events":"https://pith.science/api/pith-number/C4K53QOIWLP7Z236TW2TOINSS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4K53QOIWLP7Z236TW2TOINSS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4K53QOIWLP7Z236TW2TOINSS2/action/storage_attestation","attest_author":"https://pith.science/pith/C4K53QOIWLP7Z236TW2TOINSS2/action/author_attestation","sign_citation":"https://pith.science/pith/C4K53QOIWLP7Z236TW2TOINSS2/action/citation_signature","submit_replication":"https://pith.science/pith/C4K53QOIWLP7Z236TW2TOINSS2/action/replication_record"}},"created_at":"2026-07-05T00:20:44.121112+00:00","updated_at":"2026-07-05T00:20:44.121112+00:00"}