{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7BO3GM3CI6P3RK2MARWQH652UF","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":"c4eb803c5537025dc7ffabe7ba86e40afb16b7f4042e26ad1f2d64b734606bde","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T04:18:59Z","title_canon_sha256":"68f96cfc37bf5ec66a75d9aa62f16ec6752f8f8cc09e2f571058b8d5851fa9eb"},"schema_version":"1.0","source":{"id":"2305.10697","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10697","created_at":"2026-07-05T07:23:26Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10697v2","created_at":"2026-07-05T07:23:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10697","created_at":"2026-07-05T07:23:26Z"},{"alias_kind":"pith_short_12","alias_value":"7BO3GM3CI6P3","created_at":"2026-07-05T07:23:26Z"},{"alias_kind":"pith_short_16","alias_value":"7BO3GM3CI6P3RK2M","created_at":"2026-07-05T07:23:26Z"},{"alias_kind":"pith_short_8","alias_value":"7BO3GM3C","created_at":"2026-07-05T07:23:26Z"}],"graph_snapshots":[{"event_id":"sha256:7c89e5f5cf97878ba49281aba2530a5b935ff13c58126f864934e6899140db83","target":"graph","created_at":"2026-07-05T07:23:26Z","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/2305.10697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gauri Joshi, Jiin Woo, Yuejie Chi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T04:18:59Z","title":"The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10697","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":"sha256:18c1f7ae681daa90b93e272575387156b0177477bb60b73a4840fa4abc196019","target":"record","created_at":"2026-07-05T07:23:26Z","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":"c4eb803c5537025dc7ffabe7ba86e40afb16b7f4042e26ad1f2d64b734606bde","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T04:18:59Z","title_canon_sha256":"68f96cfc37bf5ec66a75d9aa62f16ec6752f8f8cc09e2f571058b8d5851fa9eb"},"schema_version":"1.0","source":{"id":"2305.10697","kind":"arxiv","version":2}},"canonical_sha256":"f85db33362479fb8ab4c046d03fbbaa15a0e64f571a2d96a4caa4548e653173b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f85db33362479fb8ab4c046d03fbbaa15a0e64f571a2d96a4caa4548e653173b","first_computed_at":"2026-07-05T07:23:26.247756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:26.247756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"64nE1tXhNb4fWuZC0oUoh+HZuSDy8nj3iaAf9ocsVgmIZojAecLKYL5T4MNk8TtvSeTpimEJMG9WszGEULCMDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:26.248217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10697","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18c1f7ae681daa90b93e272575387156b0177477bb60b73a4840fa4abc196019","sha256:7c89e5f5cf97878ba49281aba2530a5b935ff13c58126f864934e6899140db83"],"state_sha256":"48df91a83c2004fd8329a51893718c1f1c9d9271d61080a23fcb688c3c79c4ce"}