{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KCVMZTUNV266F7RV2YGXG57ZM5","short_pith_number":"pith:KCVMZTUN","schema_version":"1.0","canonical_sha256":"50aaccce8daebde2fe35d60d7377f9677936235556aadcdb9b01724dca5fd54d","source":{"kind":"arxiv","id":"2210.08740","version":1},"attestation_state":"computed","paper":{"title":"Risk-Sensitive Markov Decision Processes with Long-Run CVaR Criterion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"math.OC","authors_text":"Li Xia, Peter W. Glynn","submitted_at":"2022-10-17T04:29:14Z","abstract_excerpt":"CVaR (Conditional Value at Risk) is a risk metric widely used in finance. However, dynamically optimizing CVaR is difficult since it is not a standard Markov decision process (MDP) and the principle of dynamic programming fails. In this paper, we study the infinite-horizon discrete-time MDP with a long-run CVaR criterion, from the view of sensitivity-based optimization. By introducing a pseudo CVaR metric, we derive a CVaR difference formula which quantifies the difference of long-run CVaR under any two policies. The optimality of deterministic policies is derived. We obtain a so-called Bellma"},"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":"2210.08740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2022-10-17T04:29:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2b6f94f10a30845cc71c63b843e7631524ea7b726d2a7229ad34d8fc3477a374","abstract_canon_sha256":"d23cd091294868c05d7823896d367e61415ed1f4ef9a5abecb7e639394991362"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:14.510711Z","signature_b64":"S6idEySPSZ8xCcyrPT2rcoWyDTGdCL/Boilw9ZllyfBOE9IvR0eIloRNL6t+kNL+iXmWOHuqOzzR/mGS2cPgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50aaccce8daebde2fe35d60d7377f9677936235556aadcdb9b01724dca5fd54d","last_reissued_at":"2026-07-05T05:07:14.510236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:14.510236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk-Sensitive Markov Decision Processes with Long-Run CVaR Criterion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"math.OC","authors_text":"Li Xia, Peter W. Glynn","submitted_at":"2022-10-17T04:29:14Z","abstract_excerpt":"CVaR (Conditional Value at Risk) is a risk metric widely used in finance. However, dynamically optimizing CVaR is difficult since it is not a standard Markov decision process (MDP) and the principle of dynamic programming fails. In this paper, we study the infinite-horizon discrete-time MDP with a long-run CVaR criterion, from the view of sensitivity-based optimization. By introducing a pseudo CVaR metric, we derive a CVaR difference formula which quantifies the difference of long-run CVaR under any two policies. The optimality of deterministic policies is derived. We obtain a so-called Bellma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08740","kind":"arxiv","version":1},"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/2210.08740/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":"2210.08740","created_at":"2026-07-05T05:07:14.510301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.08740v1","created_at":"2026-07-05T05:07:14.510301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08740","created_at":"2026-07-05T05:07:14.510301+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCVMZTUNV266","created_at":"2026-07-05T05:07:14.510301+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCVMZTUNV266F7RV","created_at":"2026-07-05T05:07:14.510301+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCVMZTUN","created_at":"2026-07-05T05:07:14.510301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.03888","citing_title":"Measurized Markov Decision Processes","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCVMZTUNV266F7RV2YGXG57ZM5","json":"https://pith.science/pith/KCVMZTUNV266F7RV2YGXG57ZM5.json","graph_json":"https://pith.science/api/pith-number/KCVMZTUNV266F7RV2YGXG57ZM5/graph.json","events_json":"https://pith.science/api/pith-number/KCVMZTUNV266F7RV2YGXG57ZM5/events.json","paper":"https://pith.science/paper/KCVMZTUN"},"agent_actions":{"view_html":"https://pith.science/pith/KCVMZTUNV266F7RV2YGXG57ZM5","download_json":"https://pith.science/pith/KCVMZTUNV266F7RV2YGXG57ZM5.json","view_paper":"https://pith.science/paper/KCVMZTUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.08740&json=true","fetch_graph":"https://pith.science/api/pith-number/KCVMZTUNV266F7RV2YGXG57ZM5/graph.json","fetch_events":"https://pith.science/api/pith-number/KCVMZTUNV266F7RV2YGXG57ZM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCVMZTUNV266F7RV2YGXG57ZM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCVMZTUNV266F7RV2YGXG57ZM5/action/storage_attestation","attest_author":"https://pith.science/pith/KCVMZTUNV266F7RV2YGXG57ZM5/action/author_attestation","sign_citation":"https://pith.science/pith/KCVMZTUNV266F7RV2YGXG57ZM5/action/citation_signature","submit_replication":"https://pith.science/pith/KCVMZTUNV266F7RV2YGXG57ZM5/action/replication_record"}},"created_at":"2026-07-05T05:07:14.510301+00:00","updated_at":"2026-07-05T05:07:14.510301+00:00"}