{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:CIRLBJ6HKV2PHT33NFYI5JVOED","short_pith_number":"pith:CIRLBJ6H","schema_version":"1.0","canonical_sha256":"1222b0a7c75574f3cf7b69708ea6ae20f641f1735e3fa7a10d304c882c916c98","source":{"kind":"arxiv","id":"1405.2690","version":1},"attestation_state":"computed","paper":{"title":"Policy Gradients for CVaR-Constrained MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Prashanth L.A.","submitted_at":"2014-05-12T09:59:59Z","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"},"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":"1405.2690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-05-12T09:59:59Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"2f4f9fd385138f8b7e1365c8622fa8f84c27eaca8c5d7f1af8ab1702817266c1","abstract_canon_sha256":"c833a34fd903f26f3bbf0d7ce085fc325dd9ebb4f7b9ce8152d24394c90e90dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:46.154748Z","signature_b64":"ZJ6HOE9aXXqrmYZoW6Rie+CPLN11yqev678Qf0Mbonh5xpVf0fCp5Df6agtM8mmfFafN2vjC86LCkjQy7ZggBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1222b0a7c75574f3cf7b69708ea6ae20f641f1735e3fa7a10d304c882c916c98","last_reissued_at":"2026-05-18T00:02:46.154260Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:46.154260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Gradients for CVaR-Constrained MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Prashanth L.A.","submitted_at":"2014-05-12T09:59:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.2690","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":""},"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":"1405.2690","created_at":"2026-05-18T00:02:46.154328+00:00"},{"alias_kind":"arxiv_version","alias_value":"1405.2690v1","created_at":"2026-05-18T00:02:46.154328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.2690","created_at":"2026-05-18T00:02:46.154328+00:00"},{"alias_kind":"pith_short_12","alias_value":"CIRLBJ6HKV2P","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_16","alias_value":"CIRLBJ6HKV2PHT33","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_8","alias_value":"CIRLBJ6H","created_at":"2026-05-18T12:28:22.404517+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/CIRLBJ6HKV2PHT33NFYI5JVOED","json":"https://pith.science/pith/CIRLBJ6HKV2PHT33NFYI5JVOED.json","graph_json":"https://pith.science/api/pith-number/CIRLBJ6HKV2PHT33NFYI5JVOED/graph.json","events_json":"https://pith.science/api/pith-number/CIRLBJ6HKV2PHT33NFYI5JVOED/events.json","paper":"https://pith.science/paper/CIRLBJ6H"},"agent_actions":{"view_html":"https://pith.science/pith/CIRLBJ6HKV2PHT33NFYI5JVOED","download_json":"https://pith.science/pith/CIRLBJ6HKV2PHT33NFYI5JVOED.json","view_paper":"https://pith.science/paper/CIRLBJ6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1405.2690&json=true","fetch_graph":"https://pith.science/api/pith-number/CIRLBJ6HKV2PHT33NFYI5JVOED/graph.json","fetch_events":"https://pith.science/api/pith-number/CIRLBJ6HKV2PHT33NFYI5JVOED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CIRLBJ6HKV2PHT33NFYI5JVOED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CIRLBJ6HKV2PHT33NFYI5JVOED/action/storage_attestation","attest_author":"https://pith.science/pith/CIRLBJ6HKV2PHT33NFYI5JVOED/action/author_attestation","sign_citation":"https://pith.science/pith/CIRLBJ6HKV2PHT33NFYI5JVOED/action/citation_signature","submit_replication":"https://pith.science/pith/CIRLBJ6HKV2PHT33NFYI5JVOED/action/replication_record"}},"created_at":"2026-05-18T00:02:46.154328+00:00","updated_at":"2026-05-18T00:02:46.154328+00:00"}