{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O4LLDVR3WZGF7GVEJPAU674BR4","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":"646cae619b0870276db92ee76b83dcc052a43bc2d0a59f9126ed666976900fe1","cross_cats_sorted":["math.OC","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T11:17:44Z","title_canon_sha256":"10a6bbe3300863f2ebed1337e40539cdd79356282c72f28e271b8f680510cf84"},"schema_version":"1.0","source":{"id":"2209.15382","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15382","created_at":"2026-07-05T05:50:50Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15382v2","created_at":"2026-07-05T05:50:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15382","created_at":"2026-07-05T05:50:50Z"},{"alias_kind":"pith_short_12","alias_value":"O4LLDVR3WZGF","created_at":"2026-07-05T05:50:50Z"},{"alias_kind":"pith_short_16","alias_value":"O4LLDVR3WZGF7GVE","created_at":"2026-07-05T05:50:50Z"},{"alias_kind":"pith_short_8","alias_value":"O4LLDVR3","created_at":"2026-07-05T05:50:50Z"}],"graph_snapshots":[{"event_id":"sha256:68445359b293b587982ada8ecf57776b8324675a87abf810bb31c346cf48653c","target":"graph","created_at":"2026-07-05T05:50:50Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2209.15382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We analyze the convergence rate of the unregularized natural policy gradient algorithm with log-linear policy parametrizations in infinite-horizon discounted Markov decision processes. In the deterministic case, when the Q-value is known and can be approximated by a linear combination of a known feature function up to a bias error, we show that a geometrically-increasing step size yields a linear convergence rate towards an optimal policy. We then consider the sample-based case, when the best representation of the Q- value function among linear combinations of a known feature function is known","authors_text":"Carlo Alfano, Patrick Rebeschini","cross_cats":["math.OC","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T11:17:44Z","title":"Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15382","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":"sha256:3475ee9a7a975097b07a4e0c9bd89b8e464a77e134a024d91334fbe02d69dc98","target":"record","created_at":"2026-07-05T05:50:50Z","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":"646cae619b0870276db92ee76b83dcc052a43bc2d0a59f9126ed666976900fe1","cross_cats_sorted":["math.OC","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T11:17:44Z","title_canon_sha256":"10a6bbe3300863f2ebed1337e40539cdd79356282c72f28e271b8f680510cf84"},"schema_version":"1.0","source":{"id":"2209.15382","kind":"arxiv","version":2}},"canonical_sha256":"7716b1d63bb64c5f9aa44bc14f7f818f191737cdcfd1bb7a7a309d1e4def5f7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7716b1d63bb64c5f9aa44bc14f7f818f191737cdcfd1bb7a7a309d1e4def5f7c","first_computed_at":"2026-07-05T05:50:50.078016Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:50:50.078016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iGA1zpgnMg51wSzaEmpBqT+92GPoQ5AxoJEgrMqlxLtOe85x1TlYTLPHbsZXu88LUy8khTMzDEGuEwKOWxlSCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:50:50.078556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15382","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3475ee9a7a975097b07a4e0c9bd89b8e464a77e134a024d91334fbe02d69dc98","sha256:68445359b293b587982ada8ecf57776b8324675a87abf810bb31c346cf48653c"],"state_sha256":"dd01fe109f646264c4250ff3123c65e78e92b2c9987597f3ec6e345a51764078"}