{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BECHOSMOCQJHGHTW4ODOYSGEJC","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":"11610e1a51e6d9d399758ead6f877336962854eb4137d0be212cfd7a9dae7f64","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-10-20T02:57:21Z","title_canon_sha256":"8d48686ea57acb99da7b2328f5701b0a8aef787eb2a8c8c6b7351b23af532b15"},"schema_version":"1.0","source":{"id":"2110.10351","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10351","created_at":"2026-07-05T03:24:16Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10351v1","created_at":"2026-07-05T03:24:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10351","created_at":"2026-07-05T03:24:16Z"},{"alias_kind":"pith_short_12","alias_value":"BECHOSMOCQJH","created_at":"2026-07-05T03:24:16Z"},{"alias_kind":"pith_short_16","alias_value":"BECHOSMOCQJHGHTW","created_at":"2026-07-05T03:24:16Z"},{"alias_kind":"pith_short_8","alias_value":"BECHOSMO","created_at":"2026-07-05T03:24:16Z"}],"graph_snapshots":[{"event_id":"sha256:89ac4287fce207955b8e9d4b8d68663354432e11cd0729b84e42e67b8341e303","target":"graph","created_at":"2026-07-05T03:24:16Z","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/2110.10351/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The problem of constrained Markov decision process (CMDP) is investigated, where an agent aims to maximize the expected accumulated discounted reward subject to multiple constraints on its utilities/costs. A new primal-dual approach is proposed with a novel integration of three ingredients: entropy regularized policy optimizer, dual variable regularizer, and Nesterov's accelerated gradient descent dual optimizer, all of which are critical to achieve a faster convergence. The finite-time error bound of the proposed approach is characterized. Despite the challenge of the nonconcave objective sub","authors_text":"Guanghui Lan, Shaofeng Zou, Tengyu Xu, Tianjiao Li, Yingbin Liang, Ziwei Guan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-10-20T02:57:21Z","title":"Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10351","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":"sha256:19f2635babee69d564bc5b4b8ccf365dd9ed8b1c84e0638165719e0ac7caa20f","target":"record","created_at":"2026-07-05T03:24:16Z","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":"11610e1a51e6d9d399758ead6f877336962854eb4137d0be212cfd7a9dae7f64","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-10-20T02:57:21Z","title_canon_sha256":"8d48686ea57acb99da7b2328f5701b0a8aef787eb2a8c8c6b7351b23af532b15"},"schema_version":"1.0","source":{"id":"2110.10351","kind":"arxiv","version":1}},"canonical_sha256":"090477498e1412731e76e386ec48c44894130801637ab541fc216debb353b8d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"090477498e1412731e76e386ec48c44894130801637ab541fc216debb353b8d7","first_computed_at":"2026-07-05T03:24:16.250649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:16.250649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gRiEK96ujMTP9wJ5adF21Ow8lzp3WT0Rjlb1VZsHDOj4M9KZaSxccuhsSPSpsm9s35oSknt+aqA0k4fzfs16BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:16.250979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.10351","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19f2635babee69d564bc5b4b8ccf365dd9ed8b1c84e0638165719e0ac7caa20f","sha256:89ac4287fce207955b8e9d4b8d68663354432e11cd0729b84e42e67b8341e303"],"state_sha256":"6444ef48689a3f923a2091e5ad42a3a60728f090ddc510d7162b3905da647b11"}