{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AT5KM4FGLEECNAFX3SL6MENYYY","short_pith_number":"pith:AT5KM4FG","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"},"canonical_sha256":"04faa670a659082680b7dc97e611b8c613aebeacec8bdf39eba8bdfe0c720c83","source":{"kind":"arxiv","id":"1707.03770","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03770","created_at":"2026-05-18T00:20:28Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03770v2","created_at":"2026-05-18T00:20:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03770","created_at":"2026-05-18T00:20:28Z"},{"alias_kind":"pith_short_12","alias_value":"AT5KM4FGLEEC","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"AT5KM4FGLEECNAFX","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"AT5KM4FG","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AT5KM4FGLEECNAFX3SL6MENYYY","target":"record","payload":{"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"},"canonical_sha256":"04faa670a659082680b7dc97e611b8c613aebeacec8bdf39eba8bdfe0c720c83","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"},"source_kind":"arxiv","source_id":"1707.03770","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w36yqfNRS3yBK3WpCLZAYsXAnckJc5uJUAMLPf1zk+YTEZhI7oXxe6TALAAcffrYRVK/ELXb1+o+Dd14+XSyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:14:07.707024Z"},"content_sha256":"55a382feb72ffc276b4b01c896265c28f895d6a82f9a4dc68fb0ce12130fad52","schema_version":"1.0","event_id":"sha256:55a382feb72ffc276b4b01c896265c28f895d6a82f9a4dc68fb0ce12130fad52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AT5KM4FGLEECNAFX3SL6MENYYY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mfpn2lGzIPuHsP3RvmUreRJtkmq2YXCQ+lxF5VtorcwuME/OaE/gtOswP7cafOGc39NQAfgwrr6oLZBAJeaHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:14:07.707392Z"},"content_sha256":"f61f9d4a82606494e5587de087471a4a24471bebb29d8b04419fae25d2be6a39","schema_version":"1.0","event_id":"sha256:f61f9d4a82606494e5587de087471a4a24471bebb29d8b04419fae25d2be6a39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY/bundle.json","state_url":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AT5KM4FGLEECNAFX3SL6MENYYY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T01:14:07Z","links":{"resolver":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY","bundle":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY/bundle.json","state":"https://pith.science/pith/AT5KM4FGLEECNAFX3SL6MENYYY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AT5KM4FGLEECNAFX3SL6MENYYY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AT5KM4FGLEECNAFX3SL6MENYYY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bfd9985b895b592b63bc59e647a2b42174fce58b307fd3fbc49d1bb8d3f54cb9","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-07-12T15:44:22Z","title_canon_sha256":"8070aa2501e763720a15734c29c50241355d2bd0b28633693cd0591ea32abf95"},"schema_version":"1.0","source":{"id":"1707.03770","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03770","created_at":"2026-05-18T00:20:28Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03770v2","created_at":"2026-05-18T00:20:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03770","created_at":"2026-05-18T00:20:28Z"},{"alias_kind":"pith_short_12","alias_value":"AT5KM4FGLEEC","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"AT5KM4FGLEECNAFX","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"AT5KM4FG","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:f61f9d4a82606494e5587de087471a4a24471bebb29d8b04419fae25d2be6a39","target":"graph","created_at":"2026-05-18T00:20:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Adithya M. Devraj, Sean P. Meyn","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-07-12T15:44:22Z","title":"Fastest Convergence for Q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03770","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:55a382feb72ffc276b4b01c896265c28f895d6a82f9a4dc68fb0ce12130fad52","target":"record","created_at":"2026-05-18T00:20:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bfd9985b895b592b63bc59e647a2b42174fce58b307fd3fbc49d1bb8d3f54cb9","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-07-12T15:44:22Z","title_canon_sha256":"8070aa2501e763720a15734c29c50241355d2bd0b28633693cd0591ea32abf95"},"schema_version":"1.0","source":{"id":"1707.03770","kind":"arxiv","version":2}},"canonical_sha256":"04faa670a659082680b7dc97e611b8c613aebeacec8bdf39eba8bdfe0c720c83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04faa670a659082680b7dc97e611b8c613aebeacec8bdf39eba8bdfe0c720c83","first_computed_at":"2026-05-18T00:20:28.100275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:28.100275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nn1HDnBRhTpW7xG0s8adlddQmMuR20mfH/BVTKyBHEoINq5OyTmQiBXxw/thyZ4trlYrspJQRkRAnvvz7GFiDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:28.100938Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.03770","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55a382feb72ffc276b4b01c896265c28f895d6a82f9a4dc68fb0ce12130fad52","sha256:f61f9d4a82606494e5587de087471a4a24471bebb29d8b04419fae25d2be6a39"],"state_sha256":"f997418787f2addee57d1629a60dc48216e3c1998963cb9f38def35d6a179a33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dhC02ZutIadeQUaX7/cIJjAiiBUPVxhU5svS1Rb8oMkYGGb6Vo+TB4dQwukXt3hztXaVlBDTS2JTrRx2QgV/AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T01:14:07.709433Z","bundle_sha256":"1e7b64bd8ef5ca3f59f4b27bc32989cd0a15fb5ee7a60da95846dd4fb7af5e94"}}