{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5ITGTNJDXXTLYOBVZ7VEZ4MGG6","short_pith_number":"pith:5ITGTNJD","schema_version":"1.0","canonical_sha256":"ea2669b523bde6bc3835cfea4cf18637a7fa78495b67a4c9115a07d020163879","source":{"kind":"arxiv","id":"2412.14555","version":1},"attestation_state":"computed","paper":{"title":"Single-Loop Federated Actor-Critic across Heterogeneous Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Xiaowen Gong, Ye Zhu","submitted_at":"2024-12-19T06:13:59Z","abstract_excerpt":"Federated reinforcement learning (FRL) has emerged as a promising paradigm, enabling multiple agents to collaborate and learn a shared policy adaptable across heterogeneous environments. Among the various reinforcement learning (RL) algorithms, the actor-critic (AC) algorithm stands out for its low variance and high sample efficiency. However, little to nothing is known theoretically about AC in a federated manner, especially each agent interacts with a potentially different environment. The lack of such results is attributed to various technical challenges: a two-level structure illustrating "},"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":"2412.14555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T06:13:59Z","cross_cats_sorted":["cs.DC","cs.MA"],"title_canon_sha256":"245ab640fbe18bd278ea020d6fdb445b8da62784694f0c625423802a5d9e131c","abstract_canon_sha256":"fe516e9acd98203e0fbcdf6a66e3284f4dcd3ca5fe04d4ef2cb615aae378544c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:29.177157Z","signature_b64":"lNCyRMwSHZRYsVonW37YO2DHbfIA1uqbV5UsugyeD/E4yn8n/T0br/OeVyxVgQ/2lKMb1OSFgZ+gcSm85LozCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea2669b523bde6bc3835cfea4cf18637a7fa78495b67a4c9115a07d020163879","last_reissued_at":"2026-07-05T09:53:29.176357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:29.176357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single-Loop Federated Actor-Critic across Heterogeneous Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Xiaowen Gong, Ye Zhu","submitted_at":"2024-12-19T06:13:59Z","abstract_excerpt":"Federated reinforcement learning (FRL) has emerged as a promising paradigm, enabling multiple agents to collaborate and learn a shared policy adaptable across heterogeneous environments. Among the various reinforcement learning (RL) algorithms, the actor-critic (AC) algorithm stands out for its low variance and high sample efficiency. However, little to nothing is known theoretically about AC in a federated manner, especially each agent interacts with a potentially different environment. The lack of such results is attributed to various technical challenges: a two-level structure illustrating "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14555","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/2412.14555/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":"2412.14555","created_at":"2026-07-05T09:53:29.176529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14555v1","created_at":"2026-07-05T09:53:29.176529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14555","created_at":"2026-07-05T09:53:29.176529+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ITGTNJDXXTL","created_at":"2026-07-05T09:53:29.176529+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ITGTNJDXXTLYOBV","created_at":"2026-07-05T09:53:29.176529+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ITGTNJD","created_at":"2026-07-05T09:53:29.176529+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/5ITGTNJDXXTLYOBVZ7VEZ4MGG6","json":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6.json","graph_json":"https://pith.science/api/pith-number/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/graph.json","events_json":"https://pith.science/api/pith-number/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/events.json","paper":"https://pith.science/paper/5ITGTNJD"},"agent_actions":{"view_html":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6","download_json":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6.json","view_paper":"https://pith.science/paper/5ITGTNJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14555&json=true","fetch_graph":"https://pith.science/api/pith-number/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/graph.json","fetch_events":"https://pith.science/api/pith-number/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/action/storage_attestation","attest_author":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/action/author_attestation","sign_citation":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/action/citation_signature","submit_replication":"https://pith.science/pith/5ITGTNJDXXTLYOBVZ7VEZ4MGG6/action/replication_record"}},"created_at":"2026-07-05T09:53:29.176529+00:00","updated_at":"2026-07-05T09:53:29.176529+00:00"}