{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MZFPEAWNPPPVKV6XJDCXVSEYLM","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":"359f631a3ef5f2d3f83b97a760ff0311202f53425eb4757a358e5dc77a9fe0ef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T22:31:03Z","title_canon_sha256":"5c75529989bc54c3bc87a76ced16f8e4e3ede38ef7c61067fabf14d964ee2bb3"},"schema_version":"1.0","source":{"id":"2503.08934","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08934","created_at":"2026-07-05T10:37:46Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08934v3","created_at":"2026-07-05T10:37:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08934","created_at":"2026-07-05T10:37:46Z"},{"alias_kind":"pith_short_12","alias_value":"MZFPEAWNPPPV","created_at":"2026-07-05T10:37:46Z"},{"alias_kind":"pith_short_16","alias_value":"MZFPEAWNPPPVKV6X","created_at":"2026-07-05T10:37:46Z"},{"alias_kind":"pith_short_8","alias_value":"MZFPEAWN","created_at":"2026-07-05T10:37:46Z"}],"graph_snapshots":[{"event_id":"sha256:2cb4c660773e602131d05269ef765025b58dbbd254048346ddc7245228ff09b0","target":"graph","created_at":"2026-07-05T10:37:46Z","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/2503.08934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we study the sample complexity problem of risk-sensitive Reinforcement Learning (RL) with a generative model, where we aim to maximize the Conditional Value at Risk (CVaR) with risk tolerance level $\\tau$ at each step, a criterion we refer to as Iterated CVaR. We first build a connection between Iterated CVaR RL and $(s, a)$-rectangular distributional robust RL with a specific uncertainty set for CVaR. We establish nearly matching upper and lower bounds on the sample complexity of this problem. Specifically, we first prove that a value iteration-based algorithm, ICVaR-VI, achieve","authors_text":"Shaofeng Zou, Simon Khan, Zilong Deng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T22:31:03Z","title":"Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08934","kind":"arxiv","version":3},"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:e706117856dad03cda417d2160f5b75d0ad7320ee79fa06b96bca37d22a9b373","target":"record","created_at":"2026-07-05T10:37:46Z","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":"359f631a3ef5f2d3f83b97a760ff0311202f53425eb4757a358e5dc77a9fe0ef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T22:31:03Z","title_canon_sha256":"5c75529989bc54c3bc87a76ced16f8e4e3ede38ef7c61067fabf14d964ee2bb3"},"schema_version":"1.0","source":{"id":"2503.08934","kind":"arxiv","version":3}},"canonical_sha256":"664af202cd7bdf5557d748c57ac8985b2cf572ace19297a80aa57cc973763ce3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"664af202cd7bdf5557d748c57ac8985b2cf572ace19297a80aa57cc973763ce3","first_computed_at":"2026-07-05T10:37:46.895224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:46.895224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6ZOPnoL2QpZHEn6MD7EStCnmUPh+jN2OpmJdp3l7xbsBTYd8xP6Oi4bXr1rWOPfeJ2E7PweMLmDyeQ/7Zys/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:46.895779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08934","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e706117856dad03cda417d2160f5b75d0ad7320ee79fa06b96bca37d22a9b373","sha256:2cb4c660773e602131d05269ef765025b58dbbd254048346ddc7245228ff09b0"],"state_sha256":"c64cff8f77bbd13b3c397fcd657029f29cb3473a25016db8b68b996ab391d0a2"}