{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PK6C454PO57HETKQR3XXYU7URX","short_pith_number":"pith:PK6C454P","schema_version":"1.0","canonical_sha256":"7abc2e778f777e724d508eef7c53f48dde9f234d57efc0b9cdc1765107fe1197","source":{"kind":"arxiv","id":"1712.09652","version":2},"attestation_state":"computed","paper":{"title":"On Convergence of some Gradient-based Temporal-Differences Algorithms for Off-Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Huizhen Yu","submitted_at":"2017-12-27T18:43:21Z","abstract_excerpt":"We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several gradient-based TD algorithms with linear function approximation. The algorithms we analyze include: (i) two basic forms of two-time-scale gradient-based TD algorithms, which we call GTD and which minimize the mean squared projected Bellman error using stochastic gradient-descent; (ii) their \"robustified\" biased variants; (iii) their mirror-descent versions which combi"},"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":"1712.09652","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-27T18:43:21Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"03fb8bd3ad508e16624c09a39c5244c3c5411c038262752d3cf44d32fe1b7e67","abstract_canon_sha256":"a1e6c9318d1349995ffc2c52a68cff52679932dac6da6d03a1feeea17a7d6a6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:53.210868Z","signature_b64":"kaRV4Sv/efvnuWPh4ixQ/+Ro5a6DtludjqKiIUINiPRnxJ21eepLlxkiwT/oG0314g3FwQ4cJsQHMaJcaMDfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7abc2e778f777e724d508eef7c53f48dde9f234d57efc0b9cdc1765107fe1197","last_reissued_at":"2026-05-18T00:19:53.210185Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:53.210185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Convergence of some Gradient-based Temporal-Differences Algorithms for Off-Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Huizhen Yu","submitted_at":"2017-12-27T18:43:21Z","abstract_excerpt":"We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several gradient-based TD algorithms with linear function approximation. The algorithms we analyze include: (i) two basic forms of two-time-scale gradient-based TD algorithms, which we call GTD and which minimize the mean squared projected Bellman error using stochastic gradient-descent; (ii) their \"robustified\" biased variants; (iii) their mirror-descent versions which combi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09652","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":""},"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":"1712.09652","created_at":"2026-05-18T00:19:53.210289+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09652v2","created_at":"2026-05-18T00:19:53.210289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09652","created_at":"2026-05-18T00:19:53.210289+00:00"},{"alias_kind":"pith_short_12","alias_value":"PK6C454PO57H","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PK6C454PO57HETKQ","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PK6C454P","created_at":"2026-05-18T12:31:37.085036+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/PK6C454PO57HETKQR3XXYU7URX","json":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX.json","graph_json":"https://pith.science/api/pith-number/PK6C454PO57HETKQR3XXYU7URX/graph.json","events_json":"https://pith.science/api/pith-number/PK6C454PO57HETKQR3XXYU7URX/events.json","paper":"https://pith.science/paper/PK6C454P"},"agent_actions":{"view_html":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX","download_json":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX.json","view_paper":"https://pith.science/paper/PK6C454P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09652&json=true","fetch_graph":"https://pith.science/api/pith-number/PK6C454PO57HETKQR3XXYU7URX/graph.json","fetch_events":"https://pith.science/api/pith-number/PK6C454PO57HETKQR3XXYU7URX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX/action/storage_attestation","attest_author":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX/action/author_attestation","sign_citation":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX/action/citation_signature","submit_replication":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX/action/replication_record"}},"created_at":"2026-05-18T00:19:53.210289+00:00","updated_at":"2026-05-18T00:19:53.210289+00:00"}