{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AT5KM4FGLEECNAFX3SL6MENYYY","short_pith_number":"pith:AT5KM4FG","schema_version":"1.0","canonical_sha256":"04faa670a659082680b7dc97e611b8c613aebeacec8bdf39eba8bdfe0c720c83","source":{"kind":"arxiv","id":"1707.03770","version":2},"attestation_state":"computed","paper":{"title":"Fastest Convergence for Q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"cs.SY","authors_text":"Adithya M. Devraj, Sean P. Meyn","submitted_at":"2017-07-12T15:44:22Z","abstract_excerpt":"The Zap Q-learning algorithm introduced in this paper is an improvement of Watkins' original algorithm and recent competitors in several respects. It is a matrix-gain algorithm designed so that its asymptotic variance is optimal. Moreover, an ODE analysis suggests that the transient behavior is a close match to a deterministic Newton-Raphson implementation. This is made possible by a two time-scale update equation for the matrix gain sequence.\n  The analysis suggests that the approach will lead to stable and efficient computation even for non-ideal parameterized settings. Numerical experiments"},"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":"1707.03770","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-07-12T15:44:22Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"8070aa2501e763720a15734c29c50241355d2bd0b28633693cd0591ea32abf95","abstract_canon_sha256":"bfd9985b895b592b63bc59e647a2b42174fce58b307fd3fbc49d1bb8d3f54cb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:28.100938Z","signature_b64":"nn1HDnBRhTpW7xG0s8adlddQmMuR20mfH/BVTKyBHEoINq5OyTmQiBXxw/thyZ4trlYrspJQRkRAnvvz7GFiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04faa670a659082680b7dc97e611b8c613aebeacec8bdf39eba8bdfe0c720c83","last_reissued_at":"2026-05-18T00:20:28.100275Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:28.100275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fastest Convergence for Q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"cs.SY","authors_text":"Adithya M. Devraj, Sean P. Meyn","submitted_at":"2017-07-12T15:44:22Z","abstract_excerpt":"The Zap Q-learning algorithm introduced in this paper is an improvement of Watkins' original algorithm and recent competitors in several respects. It is a matrix-gain algorithm designed so that its asymptotic variance is optimal. Moreover, an ODE analysis suggests that the transient behavior is a close match to a deterministic Newton-Raphson implementation. This is made possible by a two time-scale update equation for the matrix gain sequence.\n  The analysis suggests that the approach will lead to stable and efficient computation even for non-ideal parameterized settings. Numerical experiments"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03770","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":"1707.03770","created_at":"2026-05-18T00:20:28.100393+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.03770v2","created_at":"2026-05-18T00:20:28.100393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03770","created_at":"2026-05-18T00:20:28.100393+00:00"},{"alias_kind":"pith_short_12","alias_value":"AT5KM4FGLEEC","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"AT5KM4FGLEECNAFX","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"AT5KM4FG","created_at":"2026-05-18T12:31:08.081275+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/AT5KM4FGLEECNAFX3SL6MENYYY","json":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY.json","graph_json":"https://pith.science/api/pith-number/AT5KM4FGLEECNAFX3SL6MENYYY/graph.json","events_json":"https://pith.science/api/pith-number/AT5KM4FGLEECNAFX3SL6MENYYY/events.json","paper":"https://pith.science/paper/AT5KM4FG"},"agent_actions":{"view_html":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY","download_json":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY.json","view_paper":"https://pith.science/paper/AT5KM4FG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.03770&json=true","fetch_graph":"https://pith.science/api/pith-number/AT5KM4FGLEECNAFX3SL6MENYYY/graph.json","fetch_events":"https://pith.science/api/pith-number/AT5KM4FGLEECNAFX3SL6MENYYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY/action/storage_attestation","attest_author":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY/action/author_attestation","sign_citation":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY/action/citation_signature","submit_replication":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY/action/replication_record"}},"created_at":"2026-05-18T00:20:28.100393+00:00","updated_at":"2026-05-18T00:20:28.100393+00:00"}