{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UHRPXHUUI4S6XRJ75UWXGCVX2H","short_pith_number":"pith:UHRPXHUU","schema_version":"1.0","canonical_sha256":"a1e2fb9e944725ebc53fed2d730ab7d1c039f16b99702e7c77e40f5024d62f2a","source":{"kind":"arxiv","id":"2209.04624","version":1},"attestation_state":"computed","paper":{"title":"Gradient Descent Temporal Difference-difference Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"James M. Murray, Rong J.B. Zhu","submitted_at":"2022-09-10T08:55:20Z","abstract_excerpt":"Off-policy algorithms, in which a behavior policy differs from the target policy and is used to gain experience for learning, have proven to be of great practical value in reinforcement learning. However, even for simple convex problems such as linear value function approximation, these algorithms are not guaranteed to be stable. To address this, alternative algorithms that are provably convergent in such cases have been introduced, the most well known being gradient descent temporal difference (GTD) learning. This algorithm and others like it, however, tend to converge much more slowly than c"},"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":"2209.04624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-10T08:55:20Z","cross_cats_sorted":[],"title_canon_sha256":"63022470a25a240c0eedc576f8d105f7db2b49d9f7c1999eb1b11714050c3ea0","abstract_canon_sha256":"a12f7d92f8f97d3fae8ec9181aa347ca2f44e8f074eb127366a4c91b18f0a40c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:56:03.556949Z","signature_b64":"7tCTDBWjAMXG80a0B2tXExCAtAwnvSgmv5gOIRB/R8sWibjN9F51VjlCjXs7/d/mWu6KNxEH5yua0WDWd39pDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1e2fb9e944725ebc53fed2d730ab7d1c039f16b99702e7c77e40f5024d62f2a","last_reissued_at":"2026-07-05T04:56:03.556618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:56:03.556618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Descent Temporal Difference-difference Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"James M. Murray, Rong J.B. Zhu","submitted_at":"2022-09-10T08:55:20Z","abstract_excerpt":"Off-policy algorithms, in which a behavior policy differs from the target policy and is used to gain experience for learning, have proven to be of great practical value in reinforcement learning. However, even for simple convex problems such as linear value function approximation, these algorithms are not guaranteed to be stable. To address this, alternative algorithms that are provably convergent in such cases have been introduced, the most well known being gradient descent temporal difference (GTD) learning. This algorithm and others like it, however, tend to converge much more slowly than c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04624","kind":"arxiv","version":1},"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/2209.04624/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":"2209.04624","created_at":"2026-07-05T04:56:03.556671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.04624v1","created_at":"2026-07-05T04:56:03.556671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04624","created_at":"2026-07-05T04:56:03.556671+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHRPXHUUI4S6","created_at":"2026-07-05T04:56:03.556671+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHRPXHUUI4S6XRJ7","created_at":"2026-07-05T04:56:03.556671+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHRPXHUU","created_at":"2026-07-05T04:56:03.556671+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/UHRPXHUUI4S6XRJ75UWXGCVX2H","json":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H.json","graph_json":"https://pith.science/api/pith-number/UHRPXHUUI4S6XRJ75UWXGCVX2H/graph.json","events_json":"https://pith.science/api/pith-number/UHRPXHUUI4S6XRJ75UWXGCVX2H/events.json","paper":"https://pith.science/paper/UHRPXHUU"},"agent_actions":{"view_html":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H","download_json":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H.json","view_paper":"https://pith.science/paper/UHRPXHUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.04624&json=true","fetch_graph":"https://pith.science/api/pith-number/UHRPXHUUI4S6XRJ75UWXGCVX2H/graph.json","fetch_events":"https://pith.science/api/pith-number/UHRPXHUUI4S6XRJ75UWXGCVX2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H/action/storage_attestation","attest_author":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H/action/author_attestation","sign_citation":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H/action/citation_signature","submit_replication":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H/action/replication_record"}},"created_at":"2026-07-05T04:56:03.556671+00:00","updated_at":"2026-07-05T04:56:03.556671+00:00"}