{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BP2AHTRCDHRU6J6APUCAXDS2C3","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":"ba7ccee56f6525951b5e68dcd83b31f64fdd9a20e10bdce473907e97fad0cfc3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-16T06:28:00Z","title_canon_sha256":"ae48f9e0f137b92136dd59bfb10e7cb188652d79e4892fa7c409557c24893b9f"},"schema_version":"1.0","source":{"id":"2301.06276","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.06276","created_at":"2026-07-05T05:33:29Z"},{"alias_kind":"arxiv_version","alias_value":"2301.06276v1","created_at":"2026-07-05T05:33:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06276","created_at":"2026-07-05T05:33:29Z"},{"alias_kind":"pith_short_12","alias_value":"BP2AHTRCDHRU","created_at":"2026-07-05T05:33:29Z"},{"alias_kind":"pith_short_16","alias_value":"BP2AHTRCDHRU6J6A","created_at":"2026-07-05T05:33:29Z"},{"alias_kind":"pith_short_8","alias_value":"BP2AHTRC","created_at":"2026-07-05T05:33:29Z"}],"graph_snapshots":[{"event_id":"sha256:dac010e85876ecd60b9e05bada6e33cd6a5868d6749debbdd3844b36d79cc7a6","target":"graph","created_at":"2026-07-05T05:33:29Z","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/2301.06276/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the effect of baselines in on-policy stochastic policy gradient optimization, and close the gap between the theory and practice of policy optimization methods. Our first contribution is to show that the \\emph{state value} baseline allows on-policy stochastic \\emph{natural} policy gradient (NPG) to converge to a globally optimal policy at an $O(1/t)$ rate, which was not previously known. The analysis relies on two novel findings: the expected progress of the NPG update satisfies a stochastic version of the non-uniform \\L{}ojasiewicz (N\\L{}) inequality, and with probability 1 the state ","authors_text":"Bo Dai, Csaba Szepesvari, Dale Schuurmans, Jincheng Mei, Valentin Thomas, Wesley Chung","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-16T06:28:00Z","title":"The Role of Baselines in Policy Gradient Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06276","kind":"arxiv","version":1},"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":"sha256:5cc87f6390822071267b2b67bb5999319000225029f1ba56cd1d4c4d44439847","target":"record","created_at":"2026-07-05T05:33:29Z","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":"ba7ccee56f6525951b5e68dcd83b31f64fdd9a20e10bdce473907e97fad0cfc3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-16T06:28:00Z","title_canon_sha256":"ae48f9e0f137b92136dd59bfb10e7cb188652d79e4892fa7c409557c24893b9f"},"schema_version":"1.0","source":{"id":"2301.06276","kind":"arxiv","version":1}},"canonical_sha256":"0bf403ce2219e34f27c07d040b8e5a16e3c6a47d599e55221b34fbdeadd90b3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bf403ce2219e34f27c07d040b8e5a16e3c6a47d599e55221b34fbdeadd90b3f","first_computed_at":"2026-07-05T05:33:29.887558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:33:29.887558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zpv+ZR/KKzJ3omY56GDK1uCNOMHV/7N5K6wtrzAVy8mEJnKdbQ+4JRE3UQLWGG+1kfyI/1fpAoC9+lpKCVOLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:33:29.888056Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.06276","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cc87f6390822071267b2b67bb5999319000225029f1ba56cd1d4c4d44439847","sha256:dac010e85876ecd60b9e05bada6e33cd6a5868d6749debbdd3844b36d79cc7a6"],"state_sha256":"1354db3ce055ff48f85d1d4c9ddb94e1e5aafd1b92b13ffa9dc1814a620779be"}