{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6M4BSOJGSAFVNDUGPWNJNCEK7D","short_pith_number":"pith:6M4BSOJG","schema_version":"1.0","canonical_sha256":"f338193926900b568e867d9a96888af8c1efa16dcf6d2986335d85795984f0fc","source":{"kind":"arxiv","id":"1907.05231","version":1},"attestation_state":"computed","paper":{"title":"Variance-Based Risk Estimations in Markov Processes via Transformation with State Lumping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jia Yuan Yu, Shuai Ma","submitted_at":"2019-07-09T16:04:33Z","abstract_excerpt":"Variance plays a crucial role in risk-sensitive reinforcement learning, and most risk measures can be analyzed via variance. In this paper, we consider two law-invariant risks as examples: mean-variance risk and exponential utility risk. With the aid of the state-augmentation transformation (SAT), we show that, the two risks can be estimated in Markov decision processes (MDPs) with a stochastic transition-based reward and a randomized policy. To relieve the enlarged state space, a novel definition of isotopic states is proposed for state lumping, considering the special structure of the transf"},"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":"1907.05231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-09T16:04:33Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b74a7707432b02417a2f72c0c02e792d7a146ffa18e9f2ae6391237ab788be54","abstract_canon_sha256":"49a5c6657213bce0cbcd29239495be037f79ba2a5f63e146096c3cda702ca555"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:51.082641Z","signature_b64":"u/5vzQvWPllMUWJU5GB3BVoGRkJTuxPHeBsKhqyi1mQmWX/BGaF9uKKjXPpBT7VsKpQ+tzQxN+9vfdxTtHSrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f338193926900b568e867d9a96888af8c1efa16dcf6d2986335d85795984f0fc","last_reissued_at":"2026-05-17T23:40:51.080426Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:51.080426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variance-Based Risk Estimations in Markov Processes via Transformation with State Lumping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jia Yuan Yu, Shuai Ma","submitted_at":"2019-07-09T16:04:33Z","abstract_excerpt":"Variance plays a crucial role in risk-sensitive reinforcement learning, and most risk measures can be analyzed via variance. In this paper, we consider two law-invariant risks as examples: mean-variance risk and exponential utility risk. With the aid of the state-augmentation transformation (SAT), we show that, the two risks can be estimated in Markov decision processes (MDPs) with a stochastic transition-based reward and a randomized policy. To relieve the enlarged state space, a novel definition of isotopic states is proposed for state lumping, considering the special structure of the transf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05231","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":""},"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":"1907.05231","created_at":"2026-05-17T23:40:51.080515+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.05231v1","created_at":"2026-05-17T23:40:51.080515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05231","created_at":"2026-05-17T23:40:51.080515+00:00"},{"alias_kind":"pith_short_12","alias_value":"6M4BSOJGSAFV","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6M4BSOJGSAFVNDUG","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6M4BSOJG","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6M4BSOJGSAFVNDUGPWNJNCEK7D","json":"https://pith.science/pith/6M4BSOJGSAFVNDUGPWNJNCEK7D.json","graph_json":"https://pith.science/api/pith-number/6M4BSOJGSAFVNDUGPWNJNCEK7D/graph.json","events_json":"https://pith.science/api/pith-number/6M4BSOJGSAFVNDUGPWNJNCEK7D/events.json","paper":"https://pith.science/paper/6M4BSOJG"},"agent_actions":{"view_html":"https://pith.science/pith/6M4BSOJGSAFVNDUGPWNJNCEK7D","download_json":"https://pith.science/pith/6M4BSOJGSAFVNDUGPWNJNCEK7D.json","view_paper":"https://pith.science/paper/6M4BSOJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.05231&json=true","fetch_graph":"https://pith.science/api/pith-number/6M4BSOJGSAFVNDUGPWNJNCEK7D/graph.json","fetch_events":"https://pith.science/api/pith-number/6M4BSOJGSAFVNDUGPWNJNCEK7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6M4BSOJGSAFVNDUGPWNJNCEK7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6M4BSOJGSAFVNDUGPWNJNCEK7D/action/storage_attestation","attest_author":"https://pith.science/pith/6M4BSOJGSAFVNDUGPWNJNCEK7D/action/author_attestation","sign_citation":"https://pith.science/pith/6M4BSOJGSAFVNDUGPWNJNCEK7D/action/citation_signature","submit_replication":"https://pith.science/pith/6M4BSOJGSAFVNDUGPWNJNCEK7D/action/replication_record"}},"created_at":"2026-05-17T23:40:51.080515+00:00","updated_at":"2026-05-17T23:40:51.080515+00:00"}