{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:APNOL3YGOQJCYF7B7BHXMHUOWI","short_pith_number":"pith:APNOL3YG","schema_version":"1.0","canonical_sha256":"03dae5ef0674122c17e1f84f761e8eb20d64355c6edfe169b309beb7ba09da73","source":{"kind":"arxiv","id":"1804.05950","version":2},"attestation_state":"computed","paper":{"title":"State-Augmentation Transformations for Risk-Sensitive Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jia Yuan Yu, Shuai Ma","submitted_at":"2018-04-16T21:38:40Z","abstract_excerpt":"In the framework of MDP, although the general reward function takes three arguments-current state, action, and successor state; it is often simplified to a function of two arguments-current state and action. The former is called a transition-based reward function, whereas the latter is called a state-based reward function. When the objective involves the expected cumulative reward only, this simplification works perfectly. However, when the objective is risk-sensitive, this simplification leads to an incorrect value. We present state-augmentation transformations (SATs), which preserve the rewa"},"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":"1804.05950","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-04-16T21:38:40Z","cross_cats_sorted":[],"title_canon_sha256":"51702c371a79612a60db8e8e9a5610cad3b7626d2620fb8f2f8a5fc625483aa6","abstract_canon_sha256":"37567086ed6f26736a0af1d56c2d05faf8618fc0323579fb1b5b3ebdb1d52080"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:32.813443Z","signature_b64":"kSR5pNI8CTXtM0CXY7/VvHUe8qwWIbvkbDpRvYsUTYkvssU0/L2iPWLcYcOW8JwrBCtgL80WW0i8ykGKlAoOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03dae5ef0674122c17e1f84f761e8eb20d64355c6edfe169b309beb7ba09da73","last_reissued_at":"2026-05-17T23:59:32.812722Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:32.812722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"State-Augmentation Transformations for Risk-Sensitive Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jia Yuan Yu, Shuai Ma","submitted_at":"2018-04-16T21:38:40Z","abstract_excerpt":"In the framework of MDP, although the general reward function takes three arguments-current state, action, and successor state; it is often simplified to a function of two arguments-current state and action. The former is called a transition-based reward function, whereas the latter is called a state-based reward function. When the objective involves the expected cumulative reward only, this simplification works perfectly. However, when the objective is risk-sensitive, this simplification leads to an incorrect value. We present state-augmentation transformations (SATs), which preserve the rewa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05950","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":""},"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":"1804.05950","created_at":"2026-05-17T23:59:32.812847+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.05950v2","created_at":"2026-05-17T23:59:32.812847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05950","created_at":"2026-05-17T23:59:32.812847+00:00"},{"alias_kind":"pith_short_12","alias_value":"APNOL3YGOQJC","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"APNOL3YGOQJCYF7B","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"APNOL3YG","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.04269","citing_title":"A Scheme for Dynamic Risk-Sensitive Sequential Decision Making","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05231","citing_title":"Variance-Based Risk Estimations in Markov Processes via Transformation with State Lumping","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APNOL3YGOQJCYF7B7BHXMHUOWI","json":"https://pith.science/pith/APNOL3YGOQJCYF7B7BHXMHUOWI.json","graph_json":"https://pith.science/api/pith-number/APNOL3YGOQJCYF7B7BHXMHUOWI/graph.json","events_json":"https://pith.science/api/pith-number/APNOL3YGOQJCYF7B7BHXMHUOWI/events.json","paper":"https://pith.science/paper/APNOL3YG"},"agent_actions":{"view_html":"https://pith.science/pith/APNOL3YGOQJCYF7B7BHXMHUOWI","download_json":"https://pith.science/pith/APNOL3YGOQJCYF7B7BHXMHUOWI.json","view_paper":"https://pith.science/paper/APNOL3YG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.05950&json=true","fetch_graph":"https://pith.science/api/pith-number/APNOL3YGOQJCYF7B7BHXMHUOWI/graph.json","fetch_events":"https://pith.science/api/pith-number/APNOL3YGOQJCYF7B7BHXMHUOWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APNOL3YGOQJCYF7B7BHXMHUOWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APNOL3YGOQJCYF7B7BHXMHUOWI/action/storage_attestation","attest_author":"https://pith.science/pith/APNOL3YGOQJCYF7B7BHXMHUOWI/action/author_attestation","sign_citation":"https://pith.science/pith/APNOL3YGOQJCYF7B7BHXMHUOWI/action/citation_signature","submit_replication":"https://pith.science/pith/APNOL3YGOQJCYF7B7BHXMHUOWI/action/replication_record"}},"created_at":"2026-05-17T23:59:32.812847+00:00","updated_at":"2026-05-17T23:59:32.812847+00:00"}