{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:RKKDVWEIWURAJEIMFDLTUQGIHM","short_pith_number":"pith:RKKDVWEI","schema_version":"1.0","canonical_sha256":"8a943ad888b52204910c28d73a40c83b3f7ef00b71c8aa6c67b106d7bb6be3c0","source":{"kind":"arxiv","id":"1306.1520","version":1},"attestation_state":"computed","paper":{"title":"Policy Search: Any Local Optimum Enjoys a Global Performance Guarantee","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","math.OC"],"primary_cat":"cs.LG","authors_text":"Bruno Scherrer (INRIA Nancy - Grand Est / LORIA), Matthieu Geist","submitted_at":"2013-06-06T19:27:01Z","abstract_excerpt":"Local Policy Search is a popular reinforcement learning approach for handling large state spaces. Formally, it searches locally in a paramet erized policy space in order to maximize the associated value function averaged over some predefined distribution. It is probably commonly b elieved that the best one can hope in general from such an approach is to get a local optimum of this criterion. In this article, we show th e following surprising result: \\emph{any} (approximate) \\emph{local optimum} enjoys a \\emph{global performance guarantee}. We compare this g uarantee with the one that is satisf"},"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":"1306.1520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-06T19:27:01Z","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"title_canon_sha256":"84bc940a951ee354d3607f64c1c112d0d3ba7aed9cea9eb053cf92b4ccd37b60","abstract_canon_sha256":"7f16db10d257781144fc19ee7a642d1936af3b0c0ea2fd1cf305498d3c2509d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:21:33.962237Z","signature_b64":"HKGVmJPkqKJ2ij7sijX3KqB6JPQorXE74/XWqsx1BzlVkyC2c/b5Z1KVxJY2hWkk5ySY5Sw6km5QpXAFc92KAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a943ad888b52204910c28d73a40c83b3f7ef00b71c8aa6c67b106d7bb6be3c0","last_reissued_at":"2026-05-18T03:21:33.961646Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:21:33.961646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Search: Any Local Optimum Enjoys a Global Performance Guarantee","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","math.OC"],"primary_cat":"cs.LG","authors_text":"Bruno Scherrer (INRIA Nancy - Grand Est / LORIA), Matthieu Geist","submitted_at":"2013-06-06T19:27:01Z","abstract_excerpt":"Local Policy Search is a popular reinforcement learning approach for handling large state spaces. Formally, it searches locally in a paramet erized policy space in order to maximize the associated value function averaged over some predefined distribution. It is probably commonly b elieved that the best one can hope in general from such an approach is to get a local optimum of this criterion. In this article, we show th e following surprising result: \\emph{any} (approximate) \\emph{local optimum} enjoys a \\emph{global performance guarantee}. We compare this g uarantee with the one that is satisf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.1520","kind":"arxiv","version":1},"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":"1306.1520","created_at":"2026-05-18T03:21:33.961739+00:00"},{"alias_kind":"arxiv_version","alias_value":"1306.1520v1","created_at":"2026-05-18T03:21:33.961739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.1520","created_at":"2026-05-18T03:21:33.961739+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKKDVWEIWURA","created_at":"2026-05-18T12:27:57.521954+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKKDVWEIWURAJEIM","created_at":"2026-05-18T12:27:57.521954+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKKDVWEI","created_at":"2026-05-18T12:27:57.521954+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/RKKDVWEIWURAJEIMFDLTUQGIHM","json":"https://pith.science/pith/RKKDVWEIWURAJEIMFDLTUQGIHM.json","graph_json":"https://pith.science/api/pith-number/RKKDVWEIWURAJEIMFDLTUQGIHM/graph.json","events_json":"https://pith.science/api/pith-number/RKKDVWEIWURAJEIMFDLTUQGIHM/events.json","paper":"https://pith.science/paper/RKKDVWEI"},"agent_actions":{"view_html":"https://pith.science/pith/RKKDVWEIWURAJEIMFDLTUQGIHM","download_json":"https://pith.science/pith/RKKDVWEIWURAJEIMFDLTUQGIHM.json","view_paper":"https://pith.science/paper/RKKDVWEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1306.1520&json=true","fetch_graph":"https://pith.science/api/pith-number/RKKDVWEIWURAJEIMFDLTUQGIHM/graph.json","fetch_events":"https://pith.science/api/pith-number/RKKDVWEIWURAJEIMFDLTUQGIHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKKDVWEIWURAJEIMFDLTUQGIHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKKDVWEIWURAJEIMFDLTUQGIHM/action/storage_attestation","attest_author":"https://pith.science/pith/RKKDVWEIWURAJEIMFDLTUQGIHM/action/author_attestation","sign_citation":"https://pith.science/pith/RKKDVWEIWURAJEIMFDLTUQGIHM/action/citation_signature","submit_replication":"https://pith.science/pith/RKKDVWEIWURAJEIMFDLTUQGIHM/action/replication_record"}},"created_at":"2026-05-18T03:21:33.961739+00:00","updated_at":"2026-05-18T03:21:33.961739+00:00"}