{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RIEK45G4EF2JTJWVLNAGGSL7TV","short_pith_number":"pith:RIEK45G4","schema_version":"1.0","canonical_sha256":"8a08ae74dc217499a6d55b4063497f9d4d873eede3103f76d6cf151269e68f52","source":{"kind":"arxiv","id":"2608.01917","version":1},"attestation_state":"computed","paper":{"title":"Finite-Time Analysis of Discounted Exponential-Utility Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Kumar, Ankur Naskar, Gugan Thoppe, Prashanth L. A, Vivek T A","submitted_at":"2026-08-03T08:50:07Z","abstract_excerpt":"Discounted exponential utility provides a principled criterion for risk-sensitive sequential decision-making, but its nonlinear structure complicates reinforcement learning. A recent work \\citep{thoppe2026reinforcement} addressed this difficulty by introducing a Bellman-compatible surrogate and two model-free fixed-point algorithms for optimizing it over stationary policies. However, their main convergence results are asymptotic. In this work, we establish finite-time rates of $\\tilde{O} (1/\\sqrt{n})$ for the aforementioned two algorithms under asynchronous Markovian sampling, where $n$ is the"},"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":"2608.01917","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T08:50:07Z","cross_cats_sorted":[],"title_canon_sha256":"c0ac7a2875c1318cfbf85a8d13ec11e8ee0215c081569cd8fc63f0883c0d6994","abstract_canon_sha256":"734545c5c35655b48e25f5145fa83ea7720f49b2c33e9f12f595fc16e67e899c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:07:39.569893Z","signature_b64":"QDbZw44L75K9hAABC4Zf0QArJgJaeIqNRHoqiBLhIJbOFnYfNeHLHIGGFCTJBkN3EAwIoTaEFt11gy1JHjaaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a08ae74dc217499a6d55b4063497f9d4d873eede3103f76d6cf151269e68f52","last_reissued_at":"2026-08-04T02:07:39.568225Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:07:39.568225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite-Time Analysis of Discounted Exponential-Utility Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Kumar, Ankur Naskar, Gugan Thoppe, Prashanth L. A, Vivek T A","submitted_at":"2026-08-03T08:50:07Z","abstract_excerpt":"Discounted exponential utility provides a principled criterion for risk-sensitive sequential decision-making, but its nonlinear structure complicates reinforcement learning. A recent work \\citep{thoppe2026reinforcement} addressed this difficulty by introducing a Bellman-compatible surrogate and two model-free fixed-point algorithms for optimizing it over stationary policies. However, their main convergence results are asymptotic. In this work, we establish finite-time rates of $\\tilde{O} (1/\\sqrt{n})$ for the aforementioned two algorithms under asynchronous Markovian sampling, where $n$ is the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01917","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/2608.01917/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":"2608.01917","created_at":"2026-08-04T02:07:39.569734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01917v1","created_at":"2026-08-04T02:07:39.569734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01917","created_at":"2026-08-04T02:07:39.569734+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIEK45G4EF2J","created_at":"2026-08-04T02:07:39.569734+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIEK45G4EF2JTJWV","created_at":"2026-08-04T02:07:39.569734+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIEK45G4","created_at":"2026-08-04T02:07:39.569734+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/RIEK45G4EF2JTJWVLNAGGSL7TV","json":"https://pith.science/pith/RIEK45G4EF2JTJWVLNAGGSL7TV.json","graph_json":"https://pith.science/api/pith-number/RIEK45G4EF2JTJWVLNAGGSL7TV/graph.json","events_json":"https://pith.science/api/pith-number/RIEK45G4EF2JTJWVLNAGGSL7TV/events.json","paper":"https://pith.science/paper/RIEK45G4"},"agent_actions":{"view_html":"https://pith.science/pith/RIEK45G4EF2JTJWVLNAGGSL7TV","download_json":"https://pith.science/pith/RIEK45G4EF2JTJWVLNAGGSL7TV.json","view_paper":"https://pith.science/paper/RIEK45G4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01917&json=true","fetch_graph":"https://pith.science/api/pith-number/RIEK45G4EF2JTJWVLNAGGSL7TV/graph.json","fetch_events":"https://pith.science/api/pith-number/RIEK45G4EF2JTJWVLNAGGSL7TV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIEK45G4EF2JTJWVLNAGGSL7TV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIEK45G4EF2JTJWVLNAGGSL7TV/action/storage_attestation","attest_author":"https://pith.science/pith/RIEK45G4EF2JTJWVLNAGGSL7TV/action/author_attestation","sign_citation":"https://pith.science/pith/RIEK45G4EF2JTJWVLNAGGSL7TV/action/citation_signature","submit_replication":"https://pith.science/pith/RIEK45G4EF2JTJWVLNAGGSL7TV/action/replication_record"}},"created_at":"2026-08-04T02:07:39.569734+00:00","updated_at":"2026-08-04T02:07:39.569734+00:00"}