{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KFAP4KRG3AQPFAYX52RJCU55U3","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":"c30fb6745e5c0dfad958dee9c17e3cc25dab6528ae8bfb3e709d72a9e55b6601","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-15T04:42:02Z","title_canon_sha256":"1d204e7c7fb4e965041796102d49426c1364ee4c3ec8068b9335cb5986541f1a"},"schema_version":"1.0","source":{"id":"2201.05756","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05756","created_at":"2026-07-05T04:58:14Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05756v3","created_at":"2026-07-05T04:58:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05756","created_at":"2026-07-05T04:58:14Z"},{"alias_kind":"pith_short_12","alias_value":"KFAP4KRG3AQP","created_at":"2026-07-05T04:58:14Z"},{"alias_kind":"pith_short_16","alias_value":"KFAP4KRG3AQPFAYX","created_at":"2026-07-05T04:58:14Z"},{"alias_kind":"pith_short_8","alias_value":"KFAP4KRG","created_at":"2026-07-05T04:58:14Z"}],"graph_snapshots":[{"event_id":"sha256:7808ef8c99c1db3974902d74c4e948b7af8f1b1af8fcce18c130e5721f3f5294","target":"graph","created_at":"2026-07-05T04:58:14Z","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/2201.05756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a new policy gradient (PG) methods, namely the block policy mirror descent (BPMD) method for solving a class of regularized reinforcement learning (RL) problems with (strongly)-convex regularizers. Compared to the traditional PG methods with a batch update rule, which visits and updates the policy for every state, BPMD method has cheap per-iteration computation via a partial update rule that performs the policy update on a sampled state. Despite the nonconvex nature of the problem and a partial update rule, we provide a unified analysis for several sampling schemes, a","authors_text":"Guanghui Lan, Tuo Zhao, Yan Li","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-15T04:42:02Z","title":"Block Policy Mirror Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05756","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:dc085603d5493ca1bd3428bc5b9dcd7fb590782258f23f3bebf632fd77453230","target":"record","created_at":"2026-07-05T04:58:14Z","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":"c30fb6745e5c0dfad958dee9c17e3cc25dab6528ae8bfb3e709d72a9e55b6601","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-15T04:42:02Z","title_canon_sha256":"1d204e7c7fb4e965041796102d49426c1364ee4c3ec8068b9335cb5986541f1a"},"schema_version":"1.0","source":{"id":"2201.05756","kind":"arxiv","version":3}},"canonical_sha256":"5140fe2a26d820f28317eea29153bda6f943d89599ff49d0fcfcaa13d363c8ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5140fe2a26d820f28317eea29153bda6f943d89599ff49d0fcfcaa13d363c8ab","first_computed_at":"2026-07-05T04:58:14.957087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:58:14.957087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yux+rxdEW3/Lf7i8yulkPWAI4v2ejUbOjTwuvG+RIQ+GZoKiMsxLXET72wgRzVOONrkCgGUqN3RZj7CnUp9zDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:58:14.957482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.05756","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc085603d5493ca1bd3428bc5b9dcd7fb590782258f23f3bebf632fd77453230","sha256:7808ef8c99c1db3974902d74c4e948b7af8f1b1af8fcce18c130e5721f3f5294"],"state_sha256":"bfbb83e266b6ba7d01ba9c751df27cb8652ff3e68770968d1dca51b7157a7213"}