{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TCXFQ2ASA2P5BHMT7IK4GIFSPT","short_pith_number":"pith:TCXFQ2AS","schema_version":"1.0","canonical_sha256":"98ae586812069fd09d93fa15c320b27cc02f865f78c1e4d8fce5bfcaf6eb5ca0","source":{"kind":"arxiv","id":"2410.17221","version":2},"attestation_state":"computed","paper":{"title":"Scalable spectral representations for multi-agent reinforcement learning in network MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY","math.OC"],"primary_cat":"cs.MA","authors_text":"Bo Dai, Na Li, Runyu Zhang, Zhaolin Ren","submitted_at":"2024-10-22T17:45:45Z","abstract_excerpt":"Network Markov Decision Processes (MDPs), a popular model for multi-agent control, pose a significant challenge to efficient learning due to the exponential growth of the global state-action space with the number of agents. In this work, utilizing the exponential decay property of network dynamics, we first derive scalable spectral local representations for network MDPs, which induces a network linear subspace for the local $Q$-function of each agent. Building on these local spectral representations, we design a scalable algorithmic framework for continuous state-action network MDPs, and provi"},"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":"2410.17221","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-10-22T17:45:45Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"2a9961df6c90d1e234fd256892cb1f54d4e2495ea74efebad62e131cce66f90a","abstract_canon_sha256":"cddd2aa57976c931bacfe2eabae9d7063ce63e3356489cf96ae8bcff9c51577f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:49.125037Z","signature_b64":"H0bI+lEXjPBd74zT+QBYMBNbwmDwhnhbbbLc78nRnRT0heXNmMDOybWKcCIQv5bcnu9K2+umejeZROKJGkHTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98ae586812069fd09d93fa15c320b27cc02f865f78c1e4d8fce5bfcaf6eb5ca0","last_reissued_at":"2026-07-05T09:36:49.124532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:49.124532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable spectral representations for multi-agent reinforcement learning in network MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY","math.OC"],"primary_cat":"cs.MA","authors_text":"Bo Dai, Na Li, Runyu Zhang, Zhaolin Ren","submitted_at":"2024-10-22T17:45:45Z","abstract_excerpt":"Network Markov Decision Processes (MDPs), a popular model for multi-agent control, pose a significant challenge to efficient learning due to the exponential growth of the global state-action space with the number of agents. In this work, utilizing the exponential decay property of network dynamics, we first derive scalable spectral local representations for network MDPs, which induces a network linear subspace for the local $Q$-function of each agent. Building on these local spectral representations, we design a scalable algorithmic framework for continuous state-action network MDPs, and provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17221","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/2410.17221/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":"2410.17221","created_at":"2026-07-05T09:36:49.124586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17221v2","created_at":"2026-07-05T09:36:49.124586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17221","created_at":"2026-07-05T09:36:49.124586+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCXFQ2ASA2P5","created_at":"2026-07-05T09:36:49.124586+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCXFQ2ASA2P5BHMT","created_at":"2026-07-05T09:36:49.124586+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCXFQ2AS","created_at":"2026-07-05T09:36:49.124586+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/TCXFQ2ASA2P5BHMT7IK4GIFSPT","json":"https://pith.science/pith/TCXFQ2ASA2P5BHMT7IK4GIFSPT.json","graph_json":"https://pith.science/api/pith-number/TCXFQ2ASA2P5BHMT7IK4GIFSPT/graph.json","events_json":"https://pith.science/api/pith-number/TCXFQ2ASA2P5BHMT7IK4GIFSPT/events.json","paper":"https://pith.science/paper/TCXFQ2AS"},"agent_actions":{"view_html":"https://pith.science/pith/TCXFQ2ASA2P5BHMT7IK4GIFSPT","download_json":"https://pith.science/pith/TCXFQ2ASA2P5BHMT7IK4GIFSPT.json","view_paper":"https://pith.science/paper/TCXFQ2AS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17221&json=true","fetch_graph":"https://pith.science/api/pith-number/TCXFQ2ASA2P5BHMT7IK4GIFSPT/graph.json","fetch_events":"https://pith.science/api/pith-number/TCXFQ2ASA2P5BHMT7IK4GIFSPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCXFQ2ASA2P5BHMT7IK4GIFSPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCXFQ2ASA2P5BHMT7IK4GIFSPT/action/storage_attestation","attest_author":"https://pith.science/pith/TCXFQ2ASA2P5BHMT7IK4GIFSPT/action/author_attestation","sign_citation":"https://pith.science/pith/TCXFQ2ASA2P5BHMT7IK4GIFSPT/action/citation_signature","submit_replication":"https://pith.science/pith/TCXFQ2ASA2P5BHMT7IK4GIFSPT/action/replication_record"}},"created_at":"2026-07-05T09:36:49.124586+00:00","updated_at":"2026-07-05T09:36:49.124586+00:00"}