{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4NJBO4Q42TVQJ5RXDLWNH6RSDT","short_pith_number":"pith:4NJBO4Q4","schema_version":"1.0","canonical_sha256":"e35217721cd4eb04f6371aecd3fa321cf6644905d5fa79e9af50abf99584d579","source":{"kind":"arxiv","id":"1704.04866","version":3},"attestation_state":"computed","paper":{"title":"Effective Warm Start for the Online Actor-Critic Reinforcement Learning based mHealth Intervention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Feiyun Zhu, Peng Liao","submitted_at":"2017-04-17T04:43:05Z","abstract_excerpt":"Online reinforcement learning (RL) is increasingly popular for the personalized mobile health (mHealth) intervention. It is able to personalize the type and dose of interventions according to user's ongoing statuses and changing needs. However, at the beginning of online learning, there are usually too few samples to support the RL updating, which leads to poor performances. A delay in good performance of the online learning algorithms can be especially detrimental in the mHealth, where users tend to quickly disengage with the mHealth app. To address this problem, we propose a new online RL me"},"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":"1704.04866","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-17T04:43:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"edc074be2dbb97340a7adaf9c71bfce1135642d44e8a8a669569220869bc14b1","abstract_canon_sha256":"3bd2b0a37feb2772cc8b307ea41a0ed67b80fcfebf1882e039a3ed90e2af1ebf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:08.608580Z","signature_b64":"enYOYovk+l38Y2A0aX2bYTvyfBDaeaLDwbrjK6lnAp0hKYuxc5uHPLW7wGaQLPClZE/ZSgKPdbAFijRs370OBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e35217721cd4eb04f6371aecd3fa321cf6644905d5fa79e9af50abf99584d579","last_reissued_at":"2026-05-18T00:44:08.608086Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:08.608086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Warm Start for the Online Actor-Critic Reinforcement Learning based mHealth Intervention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Feiyun Zhu, Peng Liao","submitted_at":"2017-04-17T04:43:05Z","abstract_excerpt":"Online reinforcement learning (RL) is increasingly popular for the personalized mobile health (mHealth) intervention. It is able to personalize the type and dose of interventions according to user's ongoing statuses and changing needs. However, at the beginning of online learning, there are usually too few samples to support the RL updating, which leads to poor performances. A delay in good performance of the online learning algorithms can be especially detrimental in the mHealth, where users tend to quickly disengage with the mHealth app. To address this problem, we propose a new online RL me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04866","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":""},"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":"1704.04866","created_at":"2026-05-18T00:44:08.608174+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.04866v3","created_at":"2026-05-18T00:44:08.608174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04866","created_at":"2026-05-18T00:44:08.608174+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NJBO4Q42TVQ","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NJBO4Q42TVQJ5RX","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NJBO4Q4","created_at":"2026-05-18T12:31:00.734936+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/4NJBO4Q42TVQJ5RXDLWNH6RSDT","json":"https://pith.science/pith/4NJBO4Q42TVQJ5RXDLWNH6RSDT.json","graph_json":"https://pith.science/api/pith-number/4NJBO4Q42TVQJ5RXDLWNH6RSDT/graph.json","events_json":"https://pith.science/api/pith-number/4NJBO4Q42TVQJ5RXDLWNH6RSDT/events.json","paper":"https://pith.science/paper/4NJBO4Q4"},"agent_actions":{"view_html":"https://pith.science/pith/4NJBO4Q42TVQJ5RXDLWNH6RSDT","download_json":"https://pith.science/pith/4NJBO4Q42TVQJ5RXDLWNH6RSDT.json","view_paper":"https://pith.science/paper/4NJBO4Q4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.04866&json=true","fetch_graph":"https://pith.science/api/pith-number/4NJBO4Q42TVQJ5RXDLWNH6RSDT/graph.json","fetch_events":"https://pith.science/api/pith-number/4NJBO4Q42TVQJ5RXDLWNH6RSDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NJBO4Q42TVQJ5RXDLWNH6RSDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NJBO4Q42TVQJ5RXDLWNH6RSDT/action/storage_attestation","attest_author":"https://pith.science/pith/4NJBO4Q42TVQJ5RXDLWNH6RSDT/action/author_attestation","sign_citation":"https://pith.science/pith/4NJBO4Q42TVQJ5RXDLWNH6RSDT/action/citation_signature","submit_replication":"https://pith.science/pith/4NJBO4Q42TVQJ5RXDLWNH6RSDT/action/replication_record"}},"created_at":"2026-05-18T00:44:08.608174+00:00","updated_at":"2026-05-18T00:44:08.608174+00:00"}