{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3Z2E3HHI626GY6IVBYD3BIPZQJ","short_pith_number":"pith:3Z2E3HHI","schema_version":"1.0","canonical_sha256":"de744d9ce8f6bc6c79150e07b0a1f98259d1cd11b710cf7d1aad07ea070726c1","source":{"kind":"arxiv","id":"2401.15273","version":2},"attestation_state":"computed","paper":{"title":"Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra, Chenyu Zhang, Han Wang, James Anderson","submitted_at":"2024-01-27T02:43:45Z","abstract_excerpt":"Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from different agents. However, when each agent interacts with a potentially different environment, little to nothing is known theoretically about the non-asymptotic performance of FRL algorithms. The lack of such results can be attributed to various technical challenges and their intricate interplay: Markovian sampling, linear function approximation, multiple local updates to save communication, heterogeneity in the reward func"},"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":"2401.15273","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-27T02:43:45Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"3094943727f79e31fb267e986651dc2ac034327d6ce67d8ef41b188464cff535","abstract_canon_sha256":"b18a44f91512e54e316c38721924cd0855206f77114b0adf927e7f709658ed8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:33.228518Z","signature_b64":"mRpsSKJJWfuul8ZvDns5a1ts5O4MZg5+VR4A/sqIiACc46oNt0nkZFlrFpzoktQoc5Y9yp0zHpwSFEU9GCGoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de744d9ce8f6bc6c79150e07b0a1f98259d1cd11b710cf7d1aad07ea070726c1","last_reissued_at":"2026-07-05T08:07:33.228020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:33.228020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra, Chenyu Zhang, Han Wang, James Anderson","submitted_at":"2024-01-27T02:43:45Z","abstract_excerpt":"Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from different agents. However, when each agent interacts with a potentially different environment, little to nothing is known theoretically about the non-asymptotic performance of FRL algorithms. The lack of such results can be attributed to various technical challenges and their intricate interplay: Markovian sampling, linear function approximation, multiple local updates to save communication, heterogeneity in the reward func"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15273","kind":"arxiv","version":2},"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/2401.15273/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":"2401.15273","created_at":"2026-07-05T08:07:33.228079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.15273v2","created_at":"2026-07-05T08:07:33.228079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15273","created_at":"2026-07-05T08:07:33.228079+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Z2E3HHI626G","created_at":"2026-07-05T08:07:33.228079+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Z2E3HHI626GY6IV","created_at":"2026-07-05T08:07:33.228079+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Z2E3HHI","created_at":"2026-07-05T08:07:33.228079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.03897","citing_title":"On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14423","citing_title":"Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3Z2E3HHI626GY6IVBYD3BIPZQJ","json":"https://pith.science/pith/3Z2E3HHI626GY6IVBYD3BIPZQJ.json","graph_json":"https://pith.science/api/pith-number/3Z2E3HHI626GY6IVBYD3BIPZQJ/graph.json","events_json":"https://pith.science/api/pith-number/3Z2E3HHI626GY6IVBYD3BIPZQJ/events.json","paper":"https://pith.science/paper/3Z2E3HHI"},"agent_actions":{"view_html":"https://pith.science/pith/3Z2E3HHI626GY6IVBYD3BIPZQJ","download_json":"https://pith.science/pith/3Z2E3HHI626GY6IVBYD3BIPZQJ.json","view_paper":"https://pith.science/paper/3Z2E3HHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.15273&json=true","fetch_graph":"https://pith.science/api/pith-number/3Z2E3HHI626GY6IVBYD3BIPZQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3Z2E3HHI626GY6IVBYD3BIPZQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Z2E3HHI626GY6IVBYD3BIPZQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Z2E3HHI626GY6IVBYD3BIPZQJ/action/storage_attestation","attest_author":"https://pith.science/pith/3Z2E3HHI626GY6IVBYD3BIPZQJ/action/author_attestation","sign_citation":"https://pith.science/pith/3Z2E3HHI626GY6IVBYD3BIPZQJ/action/citation_signature","submit_replication":"https://pith.science/pith/3Z2E3HHI626GY6IVBYD3BIPZQJ/action/replication_record"}},"created_at":"2026-07-05T08:07:33.228079+00:00","updated_at":"2026-07-05T08:07:33.228079+00:00"}