{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ICE2BBPNW6ENFUMR7FS3HRZOCY","short_pith_number":"pith:ICE2BBPN","schema_version":"1.0","canonical_sha256":"4089a085edb788d2d191f965b3c72e1610b5ed96a55c86a3699de3e944217969","source":{"kind":"arxiv","id":"1908.02805","version":4},"attestation_state":"computed","paper":{"title":"Fast Multi-Agent Temporal-Difference Learning via Homotopy Stochastic Primal-Dual Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"math.OC","authors_text":"Dongsheng Ding, Mihailo R. Jovanovi\\'c, Xiaohan Wei, Zhaoran Wang, Zhuoran Yang","submitted_at":"2019-08-07T19:25:37Z","abstract_excerpt":"We study the policy evaluation problem in multi-agent reinforcement learning where a group of agents, with jointly observed states and private local actions and rewards, collaborate to learn the value function of a given policy via local computation and communication over a connected undirected network. This problem arises in various large-scale multi-agent systems, including power grids, intelligent transportation systems, wireless sensor networks, and multi-agent robotics. When the dimension of state-action space is large, the temporal-difference learning with linear function approximation i"},"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":"1908.02805","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-08-07T19:25:37Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"b8d2a7ca2f4f9f6b5319b31c8d5dfd2a0cbe27cb421b9dfd96419fbc60d0edd6","abstract_canon_sha256":"fe79e7b58d59b285d76de49cbbf36c5e43324c93e77d311a089a08ece0efd213"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:12.818215Z","signature_b64":"oH54tNjzulRXAnyiSX8XNAXOKCQonSr6A5taU07lbq02f8S1HeXx/BG9r52HE6uWDoPL+EFAMneyXxOLfxukDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4089a085edb788d2d191f965b3c72e1610b5ed96a55c86a3699de3e944217969","last_reissued_at":"2026-07-05T03:29:12.817791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:12.817791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Multi-Agent Temporal-Difference Learning via Homotopy Stochastic Primal-Dual Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"math.OC","authors_text":"Dongsheng Ding, Mihailo R. Jovanovi\\'c, Xiaohan Wei, Zhaoran Wang, Zhuoran Yang","submitted_at":"2019-08-07T19:25:37Z","abstract_excerpt":"We study the policy evaluation problem in multi-agent reinforcement learning where a group of agents, with jointly observed states and private local actions and rewards, collaborate to learn the value function of a given policy via local computation and communication over a connected undirected network. This problem arises in various large-scale multi-agent systems, including power grids, intelligent transportation systems, wireless sensor networks, and multi-agent robotics. When the dimension of state-action space is large, the temporal-difference learning with linear function approximation i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02805","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.02805/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":"1908.02805","created_at":"2026-07-05T03:29:12.817849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.02805v4","created_at":"2026-07-05T03:29:12.817849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02805","created_at":"2026-07-05T03:29:12.817849+00:00"},{"alias_kind":"pith_short_12","alias_value":"ICE2BBPNW6EN","created_at":"2026-07-05T03:29:12.817849+00:00"},{"alias_kind":"pith_short_16","alias_value":"ICE2BBPNW6ENFUMR","created_at":"2026-07-05T03:29:12.817849+00:00"},{"alias_kind":"pith_short_8","alias_value":"ICE2BBPN","created_at":"2026-07-05T03:29:12.817849+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/ICE2BBPNW6ENFUMR7FS3HRZOCY","json":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY.json","graph_json":"https://pith.science/api/pith-number/ICE2BBPNW6ENFUMR7FS3HRZOCY/graph.json","events_json":"https://pith.science/api/pith-number/ICE2BBPNW6ENFUMR7FS3HRZOCY/events.json","paper":"https://pith.science/paper/ICE2BBPN"},"agent_actions":{"view_html":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY","download_json":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY.json","view_paper":"https://pith.science/paper/ICE2BBPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.02805&json=true","fetch_graph":"https://pith.science/api/pith-number/ICE2BBPNW6ENFUMR7FS3HRZOCY/graph.json","fetch_events":"https://pith.science/api/pith-number/ICE2BBPNW6ENFUMR7FS3HRZOCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY/action/storage_attestation","attest_author":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY/action/author_attestation","sign_citation":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY/action/citation_signature","submit_replication":"https://pith.science/pith/ICE2BBPNW6ENFUMR7FS3HRZOCY/action/replication_record"}},"created_at":"2026-07-05T03:29:12.817849+00:00","updated_at":"2026-07-05T03:29:12.817849+00:00"}