{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5DZ4IYXSI4J4XGRSUR5SIGTW3N","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":"07224930dfbbfbd4447868cf60ef925821e6fa8373490a3967dcd9984976796d","cross_cats_sorted":["cs.IT","cs.SY","eess.SY","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-03T17:30:07Z","title_canon_sha256":"c255473c8db4600b332c36ee5170cc922dc2045683b7bb4914e7496ef374ddee"},"schema_version":"1.0","source":{"id":"1911.00934","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.00934","created_at":"2026-07-05T00:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"1911.00934v2","created_at":"2026-07-05T00:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00934","created_at":"2026-07-05T00:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"5DZ4IYXSI4J4","created_at":"2026-07-05T00:37:18Z"},{"alias_kind":"pith_short_16","alias_value":"5DZ4IYXSI4J4XGRS","created_at":"2026-07-05T00:37:18Z"},{"alias_kind":"pith_short_8","alias_value":"5DZ4IYXS","created_at":"2026-07-05T00:37:18Z"}],"graph_snapshots":[{"event_id":"sha256:3f0cfc7a5eaecd0f1f9bcaf7c67b0da1214b40b603aaf337c20c32e67b7fe0cf","target":"graph","created_at":"2026-07-05T00:37:18Z","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/1911.00934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by the emerging use of multi-agent reinforcement learning (MARL) in engineering applications such as networked robotics, swarming drones, and sensor networks, we investigate the policy evaluation problem in a fully decentralized setting, using temporal-difference (TD) learning with linear function approximation to handle large state spaces in practice. The goal of a group of agents is to collaboratively learn the value function of a given policy from locally private rewards observed in a shared environment, through exchanging local estimates with neighbors. Despite their simplicity a","authors_text":"Gang Wang, Georgios B. Giannakis, Jun Sun, Qinmin Yang, Zaiyue Yang","cross_cats":["cs.IT","cs.SY","eess.SY","math.IT","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-03T17:30:07Z","title":"Finite-Sample Analysis of Decentralized Temporal-Difference Learning with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.00934","kind":"arxiv","version":2},"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":"sha256:1a3926c5aea21b20c18f022ae8dbbf1418fa829478216608b8b9794ce73338e8","target":"record","created_at":"2026-07-05T00:37:18Z","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":"07224930dfbbfbd4447868cf60ef925821e6fa8373490a3967dcd9984976796d","cross_cats_sorted":["cs.IT","cs.SY","eess.SY","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-03T17:30:07Z","title_canon_sha256":"c255473c8db4600b332c36ee5170cc922dc2045683b7bb4914e7496ef374ddee"},"schema_version":"1.0","source":{"id":"1911.00934","kind":"arxiv","version":2}},"canonical_sha256":"e8f3c462f24713cb9a32a47b241a76db68c5a2ec8395d5f46cac3420727d08ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8f3c462f24713cb9a32a47b241a76db68c5a2ec8395d5f46cac3420727d08ed","first_computed_at":"2026-07-05T00:37:18.563521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:37:18.563521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xoaw2JhM2dphN9HDlJUa/CwWw45UcuSCEg5d356RQTO3lH26nXePb7tt03c9zGC4YYgvIdDu/yhdaeFpOnQVBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:37:18.563940Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.00934","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a3926c5aea21b20c18f022ae8dbbf1418fa829478216608b8b9794ce73338e8","sha256:3f0cfc7a5eaecd0f1f9bcaf7c67b0da1214b40b603aaf337c20c32e67b7fe0cf"],"state_sha256":"b29824af1574d968651fdb459ddae6d701650424a604474ffc41ced61f5060dc"}