{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XCU4LJQGNHHCUE2R4IH3I3IMKM","short_pith_number":"pith:XCU4LJQG","schema_version":"1.0","canonical_sha256":"b8a9c5a60669ce2a1351e20fb46d0c533158f96b5e94c8b2bf70fde2dea068d0","source":{"kind":"arxiv","id":"2301.01045","version":2},"attestation_state":"computed","paper":{"title":"Risk-Averse MDPs under Reward Ambiguity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Chin Pang Ho, Haolin Ruan, Zhi Chen","submitted_at":"2023-01-03T11:06:30Z","abstract_excerpt":"We propose a distributionally robust return-risk model for Markov decision processes (MDPs) under risk and reward ambiguity. The proposed model optimizes the weighted average of mean and percentile performances, and it covers the distributionally robust MDPs and the distributionally robust chance-constrained MDPs (both under reward ambiguity) as special cases. By considering that the unknown reward distribution lies in a Wasserstein ambiguity set, we derive the tractable reformulation for our model. In particular, we show that that the return-risk model can also account for risk from uncertain"},"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":"2301.01045","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-03T11:06:30Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"f0a3a28fcbbdfc7fdd2876fe326cea079c934d1bcd5f7b93717e4cdbed95ed3a","abstract_canon_sha256":"c3e3e31f9e8ee5f5d9110cc8c0141cada3141850447091004c4925ccf262ceec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:34.248963Z","signature_b64":"JyalhPtjVZPySlFKt/jkUl37RxFFvVfZ7qZGdiVOrDlm5K41rJvbVSNGC+I0BRfmqayTBjvMYkDf7+AeKKM2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8a9c5a60669ce2a1351e20fb46d0c533158f96b5e94c8b2bf70fde2dea068d0","last_reissued_at":"2026-07-05T05:30:34.248547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:34.248547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk-Averse MDPs under Reward Ambiguity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Chin Pang Ho, Haolin Ruan, Zhi Chen","submitted_at":"2023-01-03T11:06:30Z","abstract_excerpt":"We propose a distributionally robust return-risk model for Markov decision processes (MDPs) under risk and reward ambiguity. The proposed model optimizes the weighted average of mean and percentile performances, and it covers the distributionally robust MDPs and the distributionally robust chance-constrained MDPs (both under reward ambiguity) as special cases. By considering that the unknown reward distribution lies in a Wasserstein ambiguity set, we derive the tractable reformulation for our model. In particular, we show that that the return-risk model can also account for risk from uncertain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01045","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/2301.01045/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":"2301.01045","created_at":"2026-07-05T05:30:34.248599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.01045v2","created_at":"2026-07-05T05:30:34.248599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01045","created_at":"2026-07-05T05:30:34.248599+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCU4LJQGNHHC","created_at":"2026-07-05T05:30:34.248599+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCU4LJQGNHHCUE2R","created_at":"2026-07-05T05:30:34.248599+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCU4LJQG","created_at":"2026-07-05T05:30:34.248599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16488","citing_title":"A Bayesian Composite Risk Approach for Stochastic Optimal Control and Markov Decision Processes","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM","json":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM.json","graph_json":"https://pith.science/api/pith-number/XCU4LJQGNHHCUE2R4IH3I3IMKM/graph.json","events_json":"https://pith.science/api/pith-number/XCU4LJQGNHHCUE2R4IH3I3IMKM/events.json","paper":"https://pith.science/paper/XCU4LJQG"},"agent_actions":{"view_html":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM","download_json":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM.json","view_paper":"https://pith.science/paper/XCU4LJQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.01045&json=true","fetch_graph":"https://pith.science/api/pith-number/XCU4LJQGNHHCUE2R4IH3I3IMKM/graph.json","fetch_events":"https://pith.science/api/pith-number/XCU4LJQGNHHCUE2R4IH3I3IMKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM/action/storage_attestation","attest_author":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM/action/author_attestation","sign_citation":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM/action/citation_signature","submit_replication":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM/action/replication_record"}},"created_at":"2026-07-05T05:30:34.248599+00:00","updated_at":"2026-07-05T05:30:34.248599+00:00"}