{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NOFFF5ZF4ACOGFJLQCN5637QNR","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":"c6bc83d374bf1d30b941bb748cb64b157879963276d59d8310102be7ef78c0c9","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-02-22T13:55:08Z","title_canon_sha256":"c2dcbcb9035a5c0cdbab7de7c56f11e5ca6e7356581951dc5f10fb9fef2949c8"},"schema_version":"1.0","source":{"id":"2302.11381","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.11381","created_at":"2026-07-05T07:15:13Z"},{"alias_kind":"arxiv_version","alias_value":"2302.11381v3","created_at":"2026-07-05T07:15:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11381","created_at":"2026-07-05T07:15:13Z"},{"alias_kind":"pith_short_12","alias_value":"NOFFF5ZF4ACO","created_at":"2026-07-05T07:15:13Z"},{"alias_kind":"pith_short_16","alias_value":"NOFFF5ZF4ACOGFJL","created_at":"2026-07-05T07:15:13Z"},{"alias_kind":"pith_short_8","alias_value":"NOFFF5ZF","created_at":"2026-07-05T07:15:13Z"}],"graph_snapshots":[{"event_id":"sha256:0d9667abf37d09bf2caeca41b7870b804b31e831feb7d6e4977de98682ef0ae1","target":"graph","created_at":"2026-07-05T07:15:13Z","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/2302.11381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy Mirror Descent (PMD) is a general family of algorithms that covers a wide range of novel and fundamental methods in reinforcement learning. Motivated by the instability of policy iteration (PI) with inexact policy evaluation, PMD algorithmically regularises the policy improvement step of PI. With exact policy evaluation, PI is known to converge linearly with a rate given by the discount factor $\\gamma$ of a Markov Decision Process. In this work, we bridge the gap between PI and PMD with exact policy evaluation and show that the dimension-free $\\gamma$-rate of PI can be achieved by the g","authors_text":"Ciara Pike-Burke, Emmeran Johnson, Patrick Rebeschini","cross_cats":["cs.LG","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-02-22T13:55:08Z","title":"Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11381","kind":"arxiv","version":3},"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":"sha256:9c597e88dbb7b2b8324b6d8e85877fc20d10c18a287ac3b98b48a8afc9173d26","target":"record","created_at":"2026-07-05T07:15:13Z","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":"c6bc83d374bf1d30b941bb748cb64b157879963276d59d8310102be7ef78c0c9","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-02-22T13:55:08Z","title_canon_sha256":"c2dcbcb9035a5c0cdbab7de7c56f11e5ca6e7356581951dc5f10fb9fef2949c8"},"schema_version":"1.0","source":{"id":"2302.11381","kind":"arxiv","version":3}},"canonical_sha256":"6b8a52f725e004e3152b809bdf6ff06c45bf72d13f5a81f657bc47c008639d3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b8a52f725e004e3152b809bdf6ff06c45bf72d13f5a81f657bc47c008639d3d","first_computed_at":"2026-07-05T07:15:13.282143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:15:13.282143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u0aqHxpq44DXGGaLg6wpe02f8+bhIVlmd6Q7lZo6iuy9pDVN3UqCAkSoKNDkW1IrlQa0DgPmtCx/2Jkq1S+iAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:15:13.282655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.11381","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c597e88dbb7b2b8324b6d8e85877fc20d10c18a287ac3b98b48a8afc9173d26","sha256:0d9667abf37d09bf2caeca41b7870b804b31e831feb7d6e4977de98682ef0ae1"],"state_sha256":"76574f9e201c2b2a5fd162b357934031481e7b43e5915497f0bbb847aacf50fd"}