{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:CIRLBJ6HKV2PHT33NFYI5JVOED","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":"c833a34fd903f26f3bbf0d7ce085fc325dd9ebb4f7b9ce8152d24394c90e90dd","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-05-12T09:59:59Z","title_canon_sha256":"2f4f9fd385138f8b7e1365c8622fa8f84c27eaca8c5d7f1af8ab1702817266c1"},"schema_version":"1.0","source":{"id":"1405.2690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.2690","created_at":"2026-05-18T00:02:46Z"},{"alias_kind":"arxiv_version","alias_value":"1405.2690v1","created_at":"2026-05-18T00:02:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.2690","created_at":"2026-05-18T00:02:46Z"},{"alias_kind":"pith_short_12","alias_value":"CIRLBJ6HKV2P","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"CIRLBJ6HKV2PHT33","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"CIRLBJ6H","created_at":"2026-05-18T12:28:22Z"}],"graph_snapshots":[{"event_id":"sha256:9ff58a94a556bf49d6429742a7896d25d3111db0f590088c4ca941659db536d1","target":"graph","created_at":"2026-05-18T00:02:46Z","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"},"paper":{"abstract_excerpt":"We study a risk-constrained version of the stochastic shortest path (SSP) problem, where the risk measure considered is Conditional Value-at-Risk (CVaR). We propose two algorithms that obtain a locally risk-optimal policy by employing four tools: stochastic approximation, mini batches, policy gradients and importance sampling. Both the algorithms incorporate a CVaR estimation procedure, along the lines of Bardou et al. [2009], which in turn is based on Rockafellar-Uryasev's representation for CVaR and utilize the likelihood ratio principle for estimating the gradient of the sum of one cost fun","authors_text":"Prashanth L.A.","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-05-12T09:59:59Z","title":"Policy Gradients for CVaR-Constrained MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.2690","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:de64296cc8074f1c61a6d99aa8ffc4c3e2c1e96bbee1aa04059ce05c66a01bc4","target":"record","created_at":"2026-05-18T00:02:46Z","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":"c833a34fd903f26f3bbf0d7ce085fc325dd9ebb4f7b9ce8152d24394c90e90dd","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-05-12T09:59:59Z","title_canon_sha256":"2f4f9fd385138f8b7e1365c8622fa8f84c27eaca8c5d7f1af8ab1702817266c1"},"schema_version":"1.0","source":{"id":"1405.2690","kind":"arxiv","version":1}},"canonical_sha256":"1222b0a7c75574f3cf7b69708ea6ae20f641f1735e3fa7a10d304c882c916c98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1222b0a7c75574f3cf7b69708ea6ae20f641f1735e3fa7a10d304c882c916c98","first_computed_at":"2026-05-18T00:02:46.154260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:46.154260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZJ6HOE9aXXqrmYZoW6Rie+CPLN11yqev678Qf0Mbonh5xpVf0fCp5Df6agtM8mmfFafN2vjC86LCkjQy7ZggBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:46.154748Z","signed_message":"canonical_sha256_bytes"},"source_id":"1405.2690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de64296cc8074f1c61a6d99aa8ffc4c3e2c1e96bbee1aa04059ce05c66a01bc4","sha256:9ff58a94a556bf49d6429742a7896d25d3111db0f590088c4ca941659db536d1"],"state_sha256":"e630663e89cf02b51f0bfc62efdbc919e6752dcfd4dcc236616108f2247a6677"}