{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZLP7INGQ3BQIOS43WD6FNJW6YE","short_pith_number":"pith:ZLP7INGQ","schema_version":"1.0","canonical_sha256":"cadff434d0d860874b9bb0fc56a6dec13918c15963bc76f28badfa2d1767d705","source":{"kind":"arxiv","id":"2206.05581","version":3},"attestation_state":"computed","paper":{"title":"Federated Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Aaron Sonabend-W, Doudou Zhou, Junwei Lu, Tianxi Cai, Yufeng Zhang, Zhaoran Wang","submitted_at":"2022-06-11T18:03:26Z","abstract_excerpt":"Evidence-based or data-driven dynamic treatment regimes are essential for personalized medicine, which can benefit from offline reinforcement learning (RL). Although massive healthcare data are available across medical institutions, they are prohibited from sharing due to privacy constraints. Besides, heterogeneity exists in different sites. As a result, federated offline RL algorithms are necessary and promising to deal with the problems. In this paper, we propose a multi-site Markov decision process model that allows for both homogeneous and heterogeneous effects across sites. The proposed m"},"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":"2206.05581","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-11T18:03:26Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"94fa80dce743ed75a6964333e1ef91f7742d7e03c3a934bc8a840c2f65992dee","abstract_canon_sha256":"55dca9e18dfcbc080d82daf4ce3ec88d393c233aa270292837eb52d672099c36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:06.807015Z","signature_b64":"OHQ2hsJTPosRd46LewgPLwpnULW1Q47Edt1+lCoCClfKjy6B5+yoOdJbSUgiG9MxoHWUpGbxY4mXqAdkwkWwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cadff434d0d860874b9bb0fc56a6dec13918c15963bc76f28badfa2d1767d705","last_reissued_at":"2026-07-05T07:38:06.806563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:06.806563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Aaron Sonabend-W, Doudou Zhou, Junwei Lu, Tianxi Cai, Yufeng Zhang, Zhaoran Wang","submitted_at":"2022-06-11T18:03:26Z","abstract_excerpt":"Evidence-based or data-driven dynamic treatment regimes are essential for personalized medicine, which can benefit from offline reinforcement learning (RL). Although massive healthcare data are available across medical institutions, they are prohibited from sharing due to privacy constraints. Besides, heterogeneity exists in different sites. As a result, federated offline RL algorithms are necessary and promising to deal with the problems. In this paper, we propose a multi-site Markov decision process model that allows for both homogeneous and heterogeneous effects across sites. The proposed m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05581","kind":"arxiv","version":3},"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/2206.05581/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":"2206.05581","created_at":"2026-07-05T07:38:06.806622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.05581v3","created_at":"2026-07-05T07:38:06.806622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05581","created_at":"2026-07-05T07:38:06.806622+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLP7INGQ3BQI","created_at":"2026-07-05T07:38:06.806622+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLP7INGQ3BQIOS43","created_at":"2026-07-05T07:38:06.806622+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLP7INGQ","created_at":"2026-07-05T07:38:06.806622+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/ZLP7INGQ3BQIOS43WD6FNJW6YE","json":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE.json","graph_json":"https://pith.science/api/pith-number/ZLP7INGQ3BQIOS43WD6FNJW6YE/graph.json","events_json":"https://pith.science/api/pith-number/ZLP7INGQ3BQIOS43WD6FNJW6YE/events.json","paper":"https://pith.science/paper/ZLP7INGQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE","download_json":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE.json","view_paper":"https://pith.science/paper/ZLP7INGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.05581&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLP7INGQ3BQIOS43WD6FNJW6YE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLP7INGQ3BQIOS43WD6FNJW6YE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE/action/storage_attestation","attest_author":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE/action/author_attestation","sign_citation":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE/action/citation_signature","submit_replication":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE/action/replication_record"}},"created_at":"2026-07-05T07:38:06.806622+00:00","updated_at":"2026-07-05T07:38:06.806622+00:00"}