{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FTPKCJFUORT7Y5MUXIVUR4BIFJ","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":"2097d63eff425abda2adfa4a6b4b8149cbabe49707f5f8a5019f33a504586e16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T16:53:20Z","title_canon_sha256":"ba694670b4dc0af7196893c4aa11b7cb962007bbaf401f86de4460398603774c"},"schema_version":"1.0","source":{"id":"2410.24128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.24128","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.24128v1","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24128","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"pith_short_12","alias_value":"FTPKCJFUORT7","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"pith_short_16","alias_value":"FTPKCJFUORT7Y5MU","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"pith_short_8","alias_value":"FTPKCJFU","created_at":"2026-07-05T09:29:20Z"}],"graph_snapshots":[{"event_id":"sha256:c0ba862d5f12213b645c19eb0eb6c18da502e52c87ac86b7512f2056e234cf27","target":"graph","created_at":"2026-07-05T09:29:20Z","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/2410.24128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Markov decision processes (MDPs), quantile risk measures such as Value-at-Risk are a standard metric for modeling RL agents' preferences for certain outcomes. This paper proposes a new Q-learning algorithm for quantile optimization in MDPs with strong convergence and performance guarantees. The algorithm leverages a new, simple dynamic program (DP) decomposition for quantile MDPs. Compared with prior work, our DP decomposition requires neither known transition probabilities nor solving complex saddle point equations and serves as a suitable foundation for other model-free RL algorithms. Our","authors_text":"Erick Delage, Esther Derman, Jia Lin Hau, Marek Petrik, Mohammad Ghavamzadeh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T16:53:20Z","title":"Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24128","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":"sha256:64cf447fdd08b28e031b62dee326e597881eb6fe446e7b79c283a76c53208bc5","target":"record","created_at":"2026-07-05T09:29:20Z","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":"2097d63eff425abda2adfa4a6b4b8149cbabe49707f5f8a5019f33a504586e16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T16:53:20Z","title_canon_sha256":"ba694670b4dc0af7196893c4aa11b7cb962007bbaf401f86de4460398603774c"},"schema_version":"1.0","source":{"id":"2410.24128","kind":"arxiv","version":1}},"canonical_sha256":"2cdea124b47467fc7594ba2b48f0282a7cbaf267d2ccd7e31e189f2151180b58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cdea124b47467fc7594ba2b48f0282a7cbaf267d2ccd7e31e189f2151180b58","first_computed_at":"2026-07-05T09:29:20.334380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:20.334380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hCc9u6Xw0BNOo5oAuyJzciZpfvTtHnlyn0ybzMuPiKseknTYUxi137dgYsujv5prGUKX7p/5oSPJMqit6KTHBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:20.334883Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.24128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64cf447fdd08b28e031b62dee326e597881eb6fe446e7b79c283a76c53208bc5","sha256:c0ba862d5f12213b645c19eb0eb6c18da502e52c87ac86b7512f2056e234cf27"],"state_sha256":"a95433978e329bc8d61b29e50a16cc7036d15dd682059c384c4718aeeb8feca5"}