{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6EZV4HPFYX2JR4JEDOLEYGYXXX","short_pith_number":"pith:6EZV4HPF","schema_version":"1.0","canonical_sha256":"f1335e1de5c5f498f1241b964c1b17bdfd8f7fee5cacd0d5468f44e17c024b75","source":{"kind":"arxiv","id":"2010.04740","version":2},"attestation_state":"computed","paper":{"title":"Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Deepak Khosla, Fan H. Hung, Navid Naderializadeh, Sean Soleyman","submitted_at":"2020-10-09T18:01:01Z","abstract_excerpt":"We propose a novel framework for value function factorization in multi-agent deep reinforcement learning (MARL) using graph neural networks (GNNs). In particular, we consider the team of agents as the set of nodes of a complete directed graph, whose edge weights are governed by an attention mechanism. Building upon this underlying graph, we introduce a mixing GNN module, which is responsible for i) factorizing the team state-action value function into individual per-agent observation-action value functions, and ii) explicit credit assignment to each agent in terms of fractions of the global te"},"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":"2010.04740","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-09T18:01:01Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"c92eea737295524ebbeaf569c3c6a79fb04fc0e400c664ff63958fe2f28ae09d","abstract_canon_sha256":"d4207901885f0048855855af1c92ecec985efdb88b482a3bbb8c58d64c48729e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:11.576218Z","signature_b64":"bB9TKEAMDhLioCr0ws1FSFGBXNaHS307jDEfzMBvs2KIfU+QMgE5ZQqAbLL/UfKedC/NehLMjSMNv3pO81c1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1335e1de5c5f498f1241b964c1b17bdfd8f7fee5cacd0d5468f44e17c024b75","last_reissued_at":"2026-07-05T02:14:11.575663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:11.575663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Deepak Khosla, Fan H. Hung, Navid Naderializadeh, Sean Soleyman","submitted_at":"2020-10-09T18:01:01Z","abstract_excerpt":"We propose a novel framework for value function factorization in multi-agent deep reinforcement learning (MARL) using graph neural networks (GNNs). In particular, we consider the team of agents as the set of nodes of a complete directed graph, whose edge weights are governed by an attention mechanism. Building upon this underlying graph, we introduce a mixing GNN module, which is responsible for i) factorizing the team state-action value function into individual per-agent observation-action value functions, and ii) explicit credit assignment to each agent in terms of fractions of the global te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04740","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/2010.04740/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":"2010.04740","created_at":"2026-07-05T02:14:11.575732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.04740v2","created_at":"2026-07-05T02:14:11.575732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04740","created_at":"2026-07-05T02:14:11.575732+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EZV4HPFYX2J","created_at":"2026-07-05T02:14:11.575732+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EZV4HPFYX2JR4JE","created_at":"2026-07-05T02:14:11.575732+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EZV4HPF","created_at":"2026-07-05T02:14:11.575732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.19253","citing_title":"Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08391","citing_title":"SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08391","citing_title":"SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EZV4HPFYX2JR4JEDOLEYGYXXX","json":"https://pith.science/pith/6EZV4HPFYX2JR4JEDOLEYGYXXX.json","graph_json":"https://pith.science/api/pith-number/6EZV4HPFYX2JR4JEDOLEYGYXXX/graph.json","events_json":"https://pith.science/api/pith-number/6EZV4HPFYX2JR4JEDOLEYGYXXX/events.json","paper":"https://pith.science/paper/6EZV4HPF"},"agent_actions":{"view_html":"https://pith.science/pith/6EZV4HPFYX2JR4JEDOLEYGYXXX","download_json":"https://pith.science/pith/6EZV4HPFYX2JR4JEDOLEYGYXXX.json","view_paper":"https://pith.science/paper/6EZV4HPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.04740&json=true","fetch_graph":"https://pith.science/api/pith-number/6EZV4HPFYX2JR4JEDOLEYGYXXX/graph.json","fetch_events":"https://pith.science/api/pith-number/6EZV4HPFYX2JR4JEDOLEYGYXXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EZV4HPFYX2JR4JEDOLEYGYXXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EZV4HPFYX2JR4JEDOLEYGYXXX/action/storage_attestation","attest_author":"https://pith.science/pith/6EZV4HPFYX2JR4JEDOLEYGYXXX/action/author_attestation","sign_citation":"https://pith.science/pith/6EZV4HPFYX2JR4JEDOLEYGYXXX/action/citation_signature","submit_replication":"https://pith.science/pith/6EZV4HPFYX2JR4JEDOLEYGYXXX/action/replication_record"}},"created_at":"2026-07-05T02:14:11.575732+00:00","updated_at":"2026-07-05T02:14:11.575732+00:00"}