{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:RKKDVWEIWURAJEIMFDLTUQGIHM","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":"7f16db10d257781144fc19ee7a642d1936af3b0c0ea2fd1cf305498d3c2509d7","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-06T19:27:01Z","title_canon_sha256":"84bc940a951ee354d3607f64c1c112d0d3ba7aed9cea9eb053cf92b4ccd37b60"},"schema_version":"1.0","source":{"id":"1306.1520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1306.1520","created_at":"2026-05-18T03:21:33Z"},{"alias_kind":"arxiv_version","alias_value":"1306.1520v1","created_at":"2026-05-18T03:21:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.1520","created_at":"2026-05-18T03:21:33Z"},{"alias_kind":"pith_short_12","alias_value":"RKKDVWEIWURA","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_16","alias_value":"RKKDVWEIWURAJEIM","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_8","alias_value":"RKKDVWEI","created_at":"2026-05-18T12:27:57Z"}],"graph_snapshots":[{"event_id":"sha256:65a682787a6a656603a352febcbdf591c601279578277d4472e90c4c710397a8","target":"graph","created_at":"2026-05-18T03:21:33Z","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":"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","authors_text":"Bruno Scherrer (INRIA Nancy - Grand Est / LORIA), Matthieu Geist","cross_cats":["cs.AI","cs.RO","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-06T19:27:01Z","title":"Policy Search: Any Local Optimum Enjoys a Global Performance Guarantee"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.1520","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":"sha256:6abd472d2c7966c422b7825d4ed7408cae074ad51c7cb59f7a1345a3dbed3d95","target":"record","created_at":"2026-05-18T03:21:33Z","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":"7f16db10d257781144fc19ee7a642d1936af3b0c0ea2fd1cf305498d3c2509d7","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-06T19:27:01Z","title_canon_sha256":"84bc940a951ee354d3607f64c1c112d0d3ba7aed9cea9eb053cf92b4ccd37b60"},"schema_version":"1.0","source":{"id":"1306.1520","kind":"arxiv","version":1}},"canonical_sha256":"8a943ad888b52204910c28d73a40c83b3f7ef00b71c8aa6c67b106d7bb6be3c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a943ad888b52204910c28d73a40c83b3f7ef00b71c8aa6c67b106d7bb6be3c0","first_computed_at":"2026-05-18T03:21:33.961646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:21:33.961646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HKGVmJPkqKJ2ij7sijX3KqB6JPQorXE74/XWqsx1BzlVkyC2c/b5Z1KVxJY2hWkk5ySY5Sw6km5QpXAFc92KAg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:21:33.962237Z","signed_message":"canonical_sha256_bytes"},"source_id":"1306.1520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6abd472d2c7966c422b7825d4ed7408cae074ad51c7cb59f7a1345a3dbed3d95","sha256:65a682787a6a656603a352febcbdf591c601279578277d4472e90c4c710397a8"],"state_sha256":"5a4fc0c603fc972a1f86ba192fe0aa00d4a4719d54af7714d3de80c9675f0359"}