{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RIEK45G4EF2JTJWVLNAGGSL7TV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"734545c5c35655b48e25f5145fa83ea7720f49b2c33e9f12f595fc16e67e899c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T08:50:07Z","title_canon_sha256":"c0ac7a2875c1318cfbf85a8d13ec11e8ee0215c081569cd8fc63f0883c0d6994"},"schema_version":"1.0","source":{"id":"2608.01917","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01917","created_at":"2026-08-04T02:07:39Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01917v1","created_at":"2026-08-04T02:07:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01917","created_at":"2026-08-04T02:07:39Z"},{"alias_kind":"pith_short_12","alias_value":"RIEK45G4EF2J","created_at":"2026-08-04T02:07:39Z"},{"alias_kind":"pith_short_16","alias_value":"RIEK45G4EF2JTJWV","created_at":"2026-08-04T02:07:39Z"},{"alias_kind":"pith_short_8","alias_value":"RIEK45G4","created_at":"2026-08-04T02:07:39Z"}],"graph_snapshots":[{"event_id":"sha256:273356f36ca26540645315815ef1a96a3d1166c4221a1747a12afead61afa8d6","target":"graph","created_at":"2026-08-04T02:07:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.01917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aditya Kumar, Ankur Naskar, Gugan Thoppe, Prashanth L. A, Vivek T A","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T08:50:07Z","title":"Finite-Time Analysis of Discounted Exponential-Utility Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01917","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8ad69f036811172135b809dfe47c918a3e9538e022efeed5753fb52dac2c9269","target":"record","created_at":"2026-08-04T02:07:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"734545c5c35655b48e25f5145fa83ea7720f49b2c33e9f12f595fc16e67e899c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T08:50:07Z","title_canon_sha256":"c0ac7a2875c1318cfbf85a8d13ec11e8ee0215c081569cd8fc63f0883c0d6994"},"schema_version":"1.0","source":{"id":"2608.01917","kind":"arxiv","version":1}},"canonical_sha256":"8a08ae74dc217499a6d55b4063497f9d4d873eede3103f76d6cf151269e68f52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a08ae74dc217499a6d55b4063497f9d4d873eede3103f76d6cf151269e68f52","first_computed_at":"2026-08-04T02:07:39.568225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:07:39.568225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QDbZw44L75K9hAABC4Zf0QArJgJaeIqNRHoqiBLhIJbOFnYfNeHLHIGGFCTJBkN3EAwIoTaEFt11gy1JHjaaCw==","signature_status":"signed_v1","signed_at":"2026-08-04T02:07:39.569893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01917","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ad69f036811172135b809dfe47c918a3e9538e022efeed5753fb52dac2c9269","sha256:273356f36ca26540645315815ef1a96a3d1166c4221a1747a12afead61afa8d6"],"state_sha256":"39232e8746037040afb306560ec9fe238a65dcd0b7830ba1f0c8da2e908fedfb"}