{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7BO3GM3CI6P3RK2MARWQH652UF","short_pith_number":"pith:7BO3GM3C","schema_version":"1.0","canonical_sha256":"f85db33362479fb8ab4c046d03fbbaa15a0e64f571a2d96a4caa4548e653173b","source":{"kind":"arxiv","id":"2305.10697","version":2},"attestation_state":"computed","paper":{"title":"The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gauri Joshi, Jiin Woo, Yuejie Chi","submitted_at":"2023-05-18T04:18:59Z","abstract_excerpt":"When the data used for reinforcement learning (RL) are collected by multiple agents in a distributed manner, federated versions of RL algorithms allow collaborative learning without the need for agents to share their local data. In this paper, we consider federated Q-learning, which aims to learn an optimal Q-function by periodically aggregating local Q-estimates trained on local data alone. Focusing on infinite-horizon tabular Markov decision processes, we provide sample complexity guarantees for both the synchronous and asynchronous variants of federated Q-learning. In both cases, our bounds"},"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":"2305.10697","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T04:18:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"68f96cfc37bf5ec66a75d9aa62f16ec6752f8f8cc09e2f571058b8d5851fa9eb","abstract_canon_sha256":"c4eb803c5537025dc7ffabe7ba86e40afb16b7f4042e26ad1f2d64b734606bde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:26.248217Z","signature_b64":"64nE1tXhNb4fWuZC0oUoh+HZuSDy8nj3iaAf9ocsVgmIZojAecLKYL5T4MNk8TtvSeTpimEJMG9WszGEULCMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f85db33362479fb8ab4c046d03fbbaa15a0e64f571a2d96a4caa4548e653173b","last_reissued_at":"2026-07-05T07:23:26.247756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:26.247756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gauri Joshi, Jiin Woo, Yuejie Chi","submitted_at":"2023-05-18T04:18:59Z","abstract_excerpt":"When the data used for reinforcement learning (RL) are collected by multiple agents in a distributed manner, federated versions of RL algorithms allow collaborative learning without the need for agents to share their local data. In this paper, we consider federated Q-learning, which aims to learn an optimal Q-function by periodically aggregating local Q-estimates trained on local data alone. Focusing on infinite-horizon tabular Markov decision processes, we provide sample complexity guarantees for both the synchronous and asynchronous variants of federated Q-learning. In both cases, our bounds"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10697","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/2305.10697/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":"2305.10697","created_at":"2026-07-05T07:23:26.247823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10697v2","created_at":"2026-07-05T07:23:26.247823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10697","created_at":"2026-07-05T07:23:26.247823+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BO3GM3CI6P3","created_at":"2026-07-05T07:23:26.247823+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BO3GM3CI6P3RK2M","created_at":"2026-07-05T07:23:26.247823+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BO3GM3C","created_at":"2026-07-05T07:23:26.247823+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/7BO3GM3CI6P3RK2MARWQH652UF","json":"https://pith.science/pith/7BO3GM3CI6P3RK2MARWQH652UF.json","graph_json":"https://pith.science/api/pith-number/7BO3GM3CI6P3RK2MARWQH652UF/graph.json","events_json":"https://pith.science/api/pith-number/7BO3GM3CI6P3RK2MARWQH652UF/events.json","paper":"https://pith.science/paper/7BO3GM3C"},"agent_actions":{"view_html":"https://pith.science/pith/7BO3GM3CI6P3RK2MARWQH652UF","download_json":"https://pith.science/pith/7BO3GM3CI6P3RK2MARWQH652UF.json","view_paper":"https://pith.science/paper/7BO3GM3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10697&json=true","fetch_graph":"https://pith.science/api/pith-number/7BO3GM3CI6P3RK2MARWQH652UF/graph.json","fetch_events":"https://pith.science/api/pith-number/7BO3GM3CI6P3RK2MARWQH652UF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BO3GM3CI6P3RK2MARWQH652UF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BO3GM3CI6P3RK2MARWQH652UF/action/storage_attestation","attest_author":"https://pith.science/pith/7BO3GM3CI6P3RK2MARWQH652UF/action/author_attestation","sign_citation":"https://pith.science/pith/7BO3GM3CI6P3RK2MARWQH652UF/action/citation_signature","submit_replication":"https://pith.science/pith/7BO3GM3CI6P3RK2MARWQH652UF/action/replication_record"}},"created_at":"2026-07-05T07:23:26.247823+00:00","updated_at":"2026-07-05T07:23:26.247823+00:00"}