{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MVWCK7Z5JK7BOADR7GOEJPJ6G4","short_pith_number":"pith:MVWCK7Z5","schema_version":"1.0","canonical_sha256":"656c257f3d4abe170071f99c44bd3e3703af78dc4e6a914ff63e7af9c6315868","source":{"kind":"arxiv","id":"2205.14327","version":2},"attestation_state":"computed","paper":{"title":"Efficient Policy Iteration for Robust Markov Decision Processes via Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kaixin Wang, Kfir Levy, Navdeep Kumar, Shie Mannor","submitted_at":"2022-05-28T04:05:20Z","abstract_excerpt":"Robust Markov decision processes (MDPs) provide a general framework to model decision problems where the system dynamics are changing or only partially known. Efficient methods for some \\texttt{sa}-rectangular robust MDPs exist, using its equivalence with reward regularized MDPs, generalizable to online settings. In comparison to \\texttt{sa}-rectangular robust MDPs, \\texttt{s}-rectangular robust MDPs are less restrictive but much more difficult to deal with. Interestingly, recent works have established the equivalence between \\texttt{s}-rectangular robust MDPs and policy regularized MDPs. But "},"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":"2205.14327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-28T04:05:20Z","cross_cats_sorted":[],"title_canon_sha256":"d7526b7450e35ecb86c1ebede14a99f79f70a0d46b51c07672a8846762f327a1","abstract_canon_sha256":"7ef80733cd13bbee6b9d6b9c4c82c138700865426042dd21477b87b0d24ee74f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:37.625487Z","signature_b64":"Adumf4YYHXKCcwn8NODSYMnHSYqBE9I/WHD83CXvrJKCaIu/k2IMWf63zmbJVIe1RUfkzQsWd0lxL08BduvSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"656c257f3d4abe170071f99c44bd3e3703af78dc4e6a914ff63e7af9c6315868","last_reissued_at":"2026-07-05T05:03:37.625027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:37.625027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Policy Iteration for Robust Markov Decision Processes via Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kaixin Wang, Kfir Levy, Navdeep Kumar, Shie Mannor","submitted_at":"2022-05-28T04:05:20Z","abstract_excerpt":"Robust Markov decision processes (MDPs) provide a general framework to model decision problems where the system dynamics are changing or only partially known. Efficient methods for some \\texttt{sa}-rectangular robust MDPs exist, using its equivalence with reward regularized MDPs, generalizable to online settings. In comparison to \\texttt{sa}-rectangular robust MDPs, \\texttt{s}-rectangular robust MDPs are less restrictive but much more difficult to deal with. Interestingly, recent works have established the equivalence between \\texttt{s}-rectangular robust MDPs and policy regularized MDPs. But "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14327","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.14327/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2205.14327","created_at":"2026-07-05T05:03:37.625096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14327v2","created_at":"2026-07-05T05:03:37.625096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14327","created_at":"2026-07-05T05:03:37.625096+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVWCK7Z5JK7B","created_at":"2026-07-05T05:03:37.625096+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVWCK7Z5JK7BOADR","created_at":"2026-07-05T05:03:37.625096+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVWCK7Z5","created_at":"2026-07-05T05:03:37.625096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.16286","citing_title":"Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4","json":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4.json","graph_json":"https://pith.science/api/pith-number/MVWCK7Z5JK7BOADR7GOEJPJ6G4/graph.json","events_json":"https://pith.science/api/pith-number/MVWCK7Z5JK7BOADR7GOEJPJ6G4/events.json","paper":"https://pith.science/paper/MVWCK7Z5"},"agent_actions":{"view_html":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4","download_json":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4.json","view_paper":"https://pith.science/paper/MVWCK7Z5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14327&json=true","fetch_graph":"https://pith.science/api/pith-number/MVWCK7Z5JK7BOADR7GOEJPJ6G4/graph.json","fetch_events":"https://pith.science/api/pith-number/MVWCK7Z5JK7BOADR7GOEJPJ6G4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4/action/storage_attestation","attest_author":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4/action/author_attestation","sign_citation":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4/action/citation_signature","submit_replication":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4/action/replication_record"}},"created_at":"2026-07-05T05:03:37.625096+00:00","updated_at":"2026-07-05T05:03:37.625096+00:00"}