{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:BX2B4SDZCZJUT3SOBXJ2KBTS6Y","short_pith_number":"pith:BX2B4SDZ","schema_version":"1.0","canonical_sha256":"0df41e4879165349ee4e0dd3a50672f6307deec48b18f3f0ff4a39e418ac4a56","source":{"kind":"arxiv","id":"1512.01629","version":3},"attestation_state":"computed","paper":{"title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"cs.AI","authors_text":"Lucas Janson, Marco Pavone, Mohammad Ghavamzadeh, Yinlam Chow","submitted_at":"2015-12-05T06:39:32Z","abstract_excerpt":"In many sequential decision-making problems one is interested in minimizing an expected cumulative cost while taking into account \\emph{risk}, i.e., increased awareness of events of small probability and high consequences. Accordingly, the objective of this paper is to present efficient reinforcement learning algorithms for risk-constrained Markov decision processes (MDPs), where risk is represented via a chance constraint or a constraint on the conditional value-at-risk (CVaR) of the cumulative cost. We collectively refer to such problems as percentile risk-constrained MDPs.\n  Specifically, w"},"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":"1512.01629","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-05T06:39:32Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"7ab69bcde3f4915a20d7639acad0e3f1f2dd47cc521b2a74c7c8d6c42c40e09c","abstract_canon_sha256":"09de375fba7c9a4bd9437a3497db8537d635e4b6b4bbf2faf33779578b693888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:55.905189Z","signature_b64":"37bOBedB9UU1FNZnkoCrKo7TO/XF5fEe5w3Qorc2IeLFAQpnohFIZxnM93gk6vOscqV3bxgoxwEiNwSjU9e/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0df41e4879165349ee4e0dd3a50672f6307deec48b18f3f0ff4a39e418ac4a56","last_reissued_at":"2026-05-18T00:46:55.904609Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:55.904609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"cs.AI","authors_text":"Lucas Janson, Marco Pavone, Mohammad Ghavamzadeh, Yinlam Chow","submitted_at":"2015-12-05T06:39:32Z","abstract_excerpt":"In many sequential decision-making problems one is interested in minimizing an expected cumulative cost while taking into account \\emph{risk}, i.e., increased awareness of events of small probability and high consequences. Accordingly, the objective of this paper is to present efficient reinforcement learning algorithms for risk-constrained Markov decision processes (MDPs), where risk is represented via a chance constraint or a constraint on the conditional value-at-risk (CVaR) of the cumulative cost. We collectively refer to such problems as percentile risk-constrained MDPs.\n  Specifically, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01629","kind":"arxiv","version":3},"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":"1512.01629","created_at":"2026-05-18T00:46:55.904698+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.01629v3","created_at":"2026-05-18T00:46:55.904698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01629","created_at":"2026-05-18T00:46:55.904698+00:00"},{"alias_kind":"pith_short_12","alias_value":"BX2B4SDZCZJU","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BX2B4SDZCZJUT3SO","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BX2B4SDZ","created_at":"2026-05-18T12:29:14.074870+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/BX2B4SDZCZJUT3SOBXJ2KBTS6Y","json":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y.json","graph_json":"https://pith.science/api/pith-number/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/graph.json","events_json":"https://pith.science/api/pith-number/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/events.json","paper":"https://pith.science/paper/BX2B4SDZ"},"agent_actions":{"view_html":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y","download_json":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y.json","view_paper":"https://pith.science/paper/BX2B4SDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.01629&json=true","fetch_graph":"https://pith.science/api/pith-number/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/action/storage_attestation","attest_author":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/action/author_attestation","sign_citation":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/action/citation_signature","submit_replication":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/action/replication_record"}},"created_at":"2026-05-18T00:46:55.904698+00:00","updated_at":"2026-05-18T00:46:55.904698+00:00"}