{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:5N2G2FEI4FREWVGDPQISYKQIN4","short_pith_number":"pith:5N2G2FEI","schema_version":"1.0","canonical_sha256":"eb746d1488e1624b54c37c112c2a086f364b7f354cb1364d2b3ccb689ebc9506","source":{"kind":"arxiv","id":"1511.07471","version":3},"attestation_state":"computed","paper":{"title":"Weak Convergence Properties of Constrained Emphatic Temporal-difference Learning with Constant and Slowly Diminishing Stepsize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huizhen Yu","submitted_at":"2015-11-23T21:29:43Z","abstract_excerpt":"We consider the emphatic temporal-difference (TD) algorithm, ETD($\\lambda$), for learning the value functions of stationary policies in a discounted, finite state and action Markov decision process. The ETD($\\lambda$) algorithm was recently proposed by Sutton, Mahmood, and White to solve a long-standing divergence problem of the standard TD algorithm when it is applied to off-policy training, where data from an exploratory policy are used to evaluate other policies of interest. The almost sure convergence of ETD($\\lambda$) has been proved in our recent work under general off-policy training co"},"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":"1511.07471","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-23T21:29:43Z","cross_cats_sorted":[],"title_canon_sha256":"2631191bc48070c9c94b80a5552585f8675c77f1b93e55dd49518bd83bc5056d","abstract_canon_sha256":"e7e8542c16b0ac17db6bb9b4c0e1f7f8e23dd10f282b6cf135cca2ebd568a47c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:28.469987Z","signature_b64":"6wK14IZThYAPQgwxFwlUgSpPUgTQdi4pXcnXnXgdhaI+c8LqJAOEdhJ+QCkCO6gXvxJTmvko2hTXntaLt/G8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb746d1488e1624b54c37c112c2a086f364b7f354cb1364d2b3ccb689ebc9506","last_reissued_at":"2026-05-18T00:52:28.469376Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:28.469376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weak Convergence Properties of Constrained Emphatic Temporal-difference Learning with Constant and Slowly Diminishing Stepsize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huizhen Yu","submitted_at":"2015-11-23T21:29:43Z","abstract_excerpt":"We consider the emphatic temporal-difference (TD) algorithm, ETD($\\lambda$), for learning the value functions of stationary policies in a discounted, finite state and action Markov decision process. The ETD($\\lambda$) algorithm was recently proposed by Sutton, Mahmood, and White to solve a long-standing divergence problem of the standard TD algorithm when it is applied to off-policy training, where data from an exploratory policy are used to evaluate other policies of interest. The almost sure convergence of ETD($\\lambda$) has been proved in our recent work under general off-policy training co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07471","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":"1511.07471","created_at":"2026-05-18T00:52:28.469452+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.07471v3","created_at":"2026-05-18T00:52:28.469452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07471","created_at":"2026-05-18T00:52:28.469452+00:00"},{"alias_kind":"pith_short_12","alias_value":"5N2G2FEI4FRE","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_16","alias_value":"5N2G2FEI4FREWVGD","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_8","alias_value":"5N2G2FEI","created_at":"2026-05-18T12:29:05.191682+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/5N2G2FEI4FREWVGDPQISYKQIN4","json":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4.json","graph_json":"https://pith.science/api/pith-number/5N2G2FEI4FREWVGDPQISYKQIN4/graph.json","events_json":"https://pith.science/api/pith-number/5N2G2FEI4FREWVGDPQISYKQIN4/events.json","paper":"https://pith.science/paper/5N2G2FEI"},"agent_actions":{"view_html":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4","download_json":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4.json","view_paper":"https://pith.science/paper/5N2G2FEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.07471&json=true","fetch_graph":"https://pith.science/api/pith-number/5N2G2FEI4FREWVGDPQISYKQIN4/graph.json","fetch_events":"https://pith.science/api/pith-number/5N2G2FEI4FREWVGDPQISYKQIN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4/action/storage_attestation","attest_author":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4/action/author_attestation","sign_citation":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4/action/citation_signature","submit_replication":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4/action/replication_record"}},"created_at":"2026-05-18T00:52:28.469452+00:00","updated_at":"2026-05-18T00:52:28.469452+00:00"}