{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DSBT6BJWAIGUROF46PVIWQE7QP","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":"eab05b6cb11f546ccca44bf4694983b9877bc12a78f479071e7b1277dff6e586","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-14T18:34:09Z","title_canon_sha256":"dca39933ed5662e607dbec29d82ecd2c51f7933671670f75d33619bfcdc02175"},"schema_version":"1.0","source":{"id":"2506.12596","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12596","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12596v1","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12596","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"pith_short_12","alias_value":"DSBT6BJWAIGU","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"pith_short_16","alias_value":"DSBT6BJWAIGUROF4","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"pith_short_8","alias_value":"DSBT6BJW","created_at":"2026-07-05T11:21:56Z"}],"graph_snapshots":[{"event_id":"sha256:ead570b91a7f83978193151b3673359114dd9be30efa5a706324e47220b7a670","target":"graph","created_at":"2026-07-05T11:21:56Z","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/2506.12596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy optimization has drawn increasing attention in reinforcement learning, particularly in the context of derivative-free methods for linear quadratic regulator (LQR) problems with unknown dynamics. This paper focuses on characterizing the robustness of derivative-free methods for solving an infinite-horizon LQR problem. To be specific, we estimate policy gradients by cost values, and study the effect of perturbations on the estimations, where the perturbations may arise from function approximations, measurement noises, etc. We show that under sufficiently small perturbations, the derivativ","authors_text":"Andreas A. Malikopoulos, Panagiotis Kounatidis, Weijian Li, Zhong-Ping Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-14T18:34:09Z","title":"On the Robustness of Derivative-free Methods for Linear Quadratic Regulator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12596","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:cbd30bb542ae539c9f3285ace2ed3cc1a9ec64c62e0d8f9dc2b0cb466f605cd6","target":"record","created_at":"2026-07-05T11:21:56Z","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":"eab05b6cb11f546ccca44bf4694983b9877bc12a78f479071e7b1277dff6e586","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-14T18:34:09Z","title_canon_sha256":"dca39933ed5662e607dbec29d82ecd2c51f7933671670f75d33619bfcdc02175"},"schema_version":"1.0","source":{"id":"2506.12596","kind":"arxiv","version":1}},"canonical_sha256":"1c833f0536020d48b8bcf3ea8b409f83e0a5c1e9d24d1cb3ab0516403d4cedd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c833f0536020d48b8bcf3ea8b409f83e0a5c1e9d24d1cb3ab0516403d4cedd5","first_computed_at":"2026-07-05T11:21:56.095150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:56.095150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4iJszg9+Y/BCSrcP8JRmh0zOSwh3rD0RMAQ06deh7H+CS6O65/TM/FIH5IPlhCdEbWU5r8T3fUGLRsZEeGMMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:56.095649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12596","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbd30bb542ae539c9f3285ace2ed3cc1a9ec64c62e0d8f9dc2b0cb466f605cd6","sha256:ead570b91a7f83978193151b3673359114dd9be30efa5a706324e47220b7a670"],"state_sha256":"d0dde775d0ba65f77c0b92674fcb6b7f20d9cd8b720bea2419c3dcdec561fe28"}