{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MPWU3WJ4LUMILHFDALZZDEA4ZO","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":"1c7ada37838543a3e5dfcb66771a257a740c09af0a13866662b9083d5ed4c0af","cross_cats_sorted":["cs.DC","cs.NI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T04:21:13Z","title_canon_sha256":"91e9d0448fc0ee066f906864984790cae657788da20c931cf8650dbf2d2a6531"},"schema_version":"1.0","source":{"id":"2404.08003","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08003","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08003v5","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08003","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"MPWU3WJ4LUMI","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"MPWU3WJ4LUMILHFD","created_at":"2026-07-05T10:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"MPWU3WJ4","created_at":"2026-07-05T10:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:2a52927e4d0e2bb0ec1c8d05f9c271ecedcf3ed5c45fa1681c4ca4c82b374994","target":"graph","created_at":"2026-07-05T10:04:38Z","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/2404.08003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To improve the efficiency of reinforcement learning (RL), we propose a novel asynchronous federated reinforcement learning (FedRL) framework termed AFedPG, which constructs a global model through collaboration among $N$ agents using policy gradient (PG) updates. To address the challenge of lagged policies in asynchronous settings, we design a delay-adaptive lookahead technique \\textit{specifically for FedRL} that can effectively handle heterogeneous arrival times of policy gradients. We analyze the theoretical global convergence bound of AFedPG, and characterize the advantage of the proposed a","authors_text":"Abolfazl Hashemi, Christopher G. Brinton, Dong-Jun Han, Guangchen Lan, Vaneet Aggarwal","cross_cats":["cs.DC","cs.NI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T04:21:13Z","title":"Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08003","kind":"arxiv","version":5},"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":"sha256:5d4bb1425689b02636160e7e17bfce2e13086da0873e6bf6e013a1129c8afe3f","target":"record","created_at":"2026-07-05T10:04:38Z","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":"1c7ada37838543a3e5dfcb66771a257a740c09af0a13866662b9083d5ed4c0af","cross_cats_sorted":["cs.DC","cs.NI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T04:21:13Z","title_canon_sha256":"91e9d0448fc0ee066f906864984790cae657788da20c931cf8650dbf2d2a6531"},"schema_version":"1.0","source":{"id":"2404.08003","kind":"arxiv","version":5}},"canonical_sha256":"63ed4dd93c5d18859ca302f391901ccb90ae71316151ced117703f4b013f43dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63ed4dd93c5d18859ca302f391901ccb90ae71316151ced117703f4b013f43dc","first_computed_at":"2026-07-05T10:04:38.288816Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:38.288816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aBQtS3ywMKfNI2b5eAPJe/77xmJiG27ahATiJjf2aqrrDDFzVUp7cPY5KKK5PQSgbob2CfXlQ2orYKxS5AJnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:38.289366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.08003","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d4bb1425689b02636160e7e17bfce2e13086da0873e6bf6e013a1129c8afe3f","sha256:2a52927e4d0e2bb0ec1c8d05f9c271ecedcf3ed5c45fa1681c4ca4c82b374994"],"state_sha256":"3e8b57460cf2cee579f4e78295e388379d87339e76e24fa5ccebbcc90633dfa5"}