{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VTPTC7T2CRQ4PQ6OUTT5P223VC","short_pith_number":"pith:VTPTC7T2","schema_version":"1.0","canonical_sha256":"acdf317e7a1461c7c3cea4e7d7eb5ba8b734daa4623f34511348ca94b68d627b","source":{"kind":"arxiv","id":"2112.02813","version":1},"attestation_state":"computed","paper":{"title":"MDPGT: Momentum-based Decentralized Policy Gradient Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Balu, Chinmay Hegde, Kai Liang Tan, Sin Yong Tan, Soumik Sarkar, Xian Yeow Lee, Young M. Lee, Zhanhong Jiang","submitted_at":"2021-12-06T06:55:51Z","abstract_excerpt":"We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations. Specifically, we propose a momentum-based decentralized policy gradient tracking (MDPGT) where a new momentum-based variance reduction technique is used to approximate the local policy gradient surrogate with importance sampling, and an intermediate parameter is adopted to track two consecutive policy gradient surrogates. Moreover, MDPGT provably achieves the best available sample complexity of $\\mathca"},"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":"2112.02813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T06:55:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37bd93db9825b825fcd49dc7f301f18bf0dabbd2b5f9dd7cd7a1c73b54dd4c92","abstract_canon_sha256":"4cee27af7772d183489e810b4b16a9c17b709e8ec52bc1b9acf84580411920ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:58.030697Z","signature_b64":"+UtwqQ1TpNwQzh5KFHn1lf2biDd513A2r7FmTPIpqbUXhNZWxW8rO6wX2rovh6YgpnGuchmSL6NGQfAYv1d/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acdf317e7a1461c7c3cea4e7d7eb5ba8b734daa4623f34511348ca94b68d627b","last_reissued_at":"2026-07-05T03:37:58.030014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:58.030014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MDPGT: Momentum-based Decentralized Policy Gradient Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Balu, Chinmay Hegde, Kai Liang Tan, Sin Yong Tan, Soumik Sarkar, Xian Yeow Lee, Young M. Lee, Zhanhong Jiang","submitted_at":"2021-12-06T06:55:51Z","abstract_excerpt":"We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations. Specifically, we propose a momentum-based decentralized policy gradient tracking (MDPGT) where a new momentum-based variance reduction technique is used to approximate the local policy gradient surrogate with importance sampling, and an intermediate parameter is adopted to track two consecutive policy gradient surrogates. Moreover, MDPGT provably achieves the best available sample complexity of $\\mathca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02813","kind":"arxiv","version":1},"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/2112.02813/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":"2112.02813","created_at":"2026-07-05T03:37:58.030121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.02813v1","created_at":"2026-07-05T03:37:58.030121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02813","created_at":"2026-07-05T03:37:58.030121+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTPTC7T2CRQ4","created_at":"2026-07-05T03:37:58.030121+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTPTC7T2CRQ4PQ6O","created_at":"2026-07-05T03:37:58.030121+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTPTC7T2","created_at":"2026-07-05T03:37:58.030121+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/VTPTC7T2CRQ4PQ6OUTT5P223VC","json":"https://pith.science/pith/VTPTC7T2CRQ4PQ6OUTT5P223VC.json","graph_json":"https://pith.science/api/pith-number/VTPTC7T2CRQ4PQ6OUTT5P223VC/graph.json","events_json":"https://pith.science/api/pith-number/VTPTC7T2CRQ4PQ6OUTT5P223VC/events.json","paper":"https://pith.science/paper/VTPTC7T2"},"agent_actions":{"view_html":"https://pith.science/pith/VTPTC7T2CRQ4PQ6OUTT5P223VC","download_json":"https://pith.science/pith/VTPTC7T2CRQ4PQ6OUTT5P223VC.json","view_paper":"https://pith.science/paper/VTPTC7T2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.02813&json=true","fetch_graph":"https://pith.science/api/pith-number/VTPTC7T2CRQ4PQ6OUTT5P223VC/graph.json","fetch_events":"https://pith.science/api/pith-number/VTPTC7T2CRQ4PQ6OUTT5P223VC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTPTC7T2CRQ4PQ6OUTT5P223VC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTPTC7T2CRQ4PQ6OUTT5P223VC/action/storage_attestation","attest_author":"https://pith.science/pith/VTPTC7T2CRQ4PQ6OUTT5P223VC/action/author_attestation","sign_citation":"https://pith.science/pith/VTPTC7T2CRQ4PQ6OUTT5P223VC/action/citation_signature","submit_replication":"https://pith.science/pith/VTPTC7T2CRQ4PQ6OUTT5P223VC/action/replication_record"}},"created_at":"2026-07-05T03:37:58.030121+00:00","updated_at":"2026-07-05T03:37:58.030121+00:00"}