{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:R6WUXAEVFH3DVDC4G7TO3NFFSF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"67ee0706879901fd4d856814d2fea2ff229341b82f00000b344d8f579f55b1cb","cross_cats_sorted":["cs.MA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-24T12:48:08Z","title_canon_sha256":"f0be4114bb997d605f6cc80a83fc4994dc1c21e15a3239d2fa3ca8b291ddec09"},"schema_version":"1.0","source":{"id":"2103.13147","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.13147","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"arxiv_version","alias_value":"2103.13147v1","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13147","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"pith_short_12","alias_value":"R6WUXAEVFH3D","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"R6WUXAEVFH3DVDC4","created_at":"2026-07-05T02:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"R6WUXAEV","created_at":"2026-07-05T02:26:06Z"}],"graph_snapshots":[{"event_id":"sha256:b1a1e3766a05c3e5a63518cc968646b16d22e035832a36da638318ccac5f59fc","target":"graph","created_at":"2026-07-05T02:26:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.13147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The finite-time convergence of off-policy TD learning has been comprehensively studied recently. However, such a type of convergence has not been well established for off-policy TD learning in the multi-agent setting, which covers broader applications and is fundamentally more challenging. This work develops two decentralized TD with correction (TDC) algorithms for multi-agent off-policy TD learning under Markovian sampling. In particular, our algorithms preserve full privacy of the actions, policies and rewards of the agents, and adopt mini-batch sampling to reduce the sampling variance and c","authors_text":"Rongrong Chen, Yi Zhou, Ziyi Chen","cross_cats":["cs.MA","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-24T12:48:08Z","title":"Multi-Agent Off-Policy TD Learning: Finite-Time Analysis with Near-Optimal Sample Complexity and Communication Complexity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13147","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3c0e2e1158e4a7f2386a7b5e28bc3f6cb4393a7c1975d4c05b811389cea5b96f","target":"record","created_at":"2026-07-05T02:26:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"67ee0706879901fd4d856814d2fea2ff229341b82f00000b344d8f579f55b1cb","cross_cats_sorted":["cs.MA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-24T12:48:08Z","title_canon_sha256":"f0be4114bb997d605f6cc80a83fc4994dc1c21e15a3239d2fa3ca8b291ddec09"},"schema_version":"1.0","source":{"id":"2103.13147","kind":"arxiv","version":1}},"canonical_sha256":"8fad4b809529f63a8c5c37e6edb4a59140c458abe48fe1f847dbbf5916f4069a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fad4b809529f63a8c5c37e6edb4a59140c458abe48fe1f847dbbf5916f4069a","first_computed_at":"2026-07-05T02:26:06.398004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:06.398004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8+6/0pMDl/2e5nUrWMVnffLlAPRd2IQim733FnAsgNhW48xWUc2WJ4FKoJfup2MrRyQuCJl9j9GMNGrfVz7TAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:06.398406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.13147","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c0e2e1158e4a7f2386a7b5e28bc3f6cb4393a7c1975d4c05b811389cea5b96f","sha256:b1a1e3766a05c3e5a63518cc968646b16d22e035832a36da638318ccac5f59fc"],"state_sha256":"dde3be63b0e01bd41ff7802417584b4814be2e668a929e8c1d3a3fa5b21f7229"}