{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:BX2B4SDZCZJUT3SOBXJ2KBTS6Y","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":"09de375fba7c9a4bd9437a3497db8537d635e4b6b4bbf2faf33779578b693888","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-05T06:39:32Z","title_canon_sha256":"7ab69bcde3f4915a20d7639acad0e3f1f2dd47cc521b2a74c7c8d6c42c40e09c"},"schema_version":"1.0","source":{"id":"1512.01629","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.01629","created_at":"2026-05-18T00:46:55Z"},{"alias_kind":"arxiv_version","alias_value":"1512.01629v3","created_at":"2026-05-18T00:46:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01629","created_at":"2026-05-18T00:46:55Z"},{"alias_kind":"pith_short_12","alias_value":"BX2B4SDZCZJU","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"BX2B4SDZCZJUT3SO","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"BX2B4SDZ","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:36ba644c7c0e7be07a5b61e56b95589c96d6095e55daeea7b0a11d73eeddfbbb","target":"graph","created_at":"2026-05-18T00:46:55Z","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":"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","authors_text":"Lucas Janson, Marco Pavone, Mohammad Ghavamzadeh, Yinlam Chow","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-05T06:39:32Z","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01629","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":"sha256:42ae9fbb52cb67592d99bce875ef5af4f7fe481705b17ea8e3a130cfcca8f9a7","target":"record","created_at":"2026-05-18T00:46:55Z","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":"09de375fba7c9a4bd9437a3497db8537d635e4b6b4bbf2faf33779578b693888","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-05T06:39:32Z","title_canon_sha256":"7ab69bcde3f4915a20d7639acad0e3f1f2dd47cc521b2a74c7c8d6c42c40e09c"},"schema_version":"1.0","source":{"id":"1512.01629","kind":"arxiv","version":3}},"canonical_sha256":"0df41e4879165349ee4e0dd3a50672f6307deec48b18f3f0ff4a39e418ac4a56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0df41e4879165349ee4e0dd3a50672f6307deec48b18f3f0ff4a39e418ac4a56","first_computed_at":"2026-05-18T00:46:55.904609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:55.904609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"37bOBedB9UU1FNZnkoCrKo7TO/XF5fEe5w3Qorc2IeLFAQpnohFIZxnM93gk6vOscqV3bxgoxwEiNwSjU9e/BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:55.905189Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.01629","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42ae9fbb52cb67592d99bce875ef5af4f7fe481705b17ea8e3a130cfcca8f9a7","sha256:36ba644c7c0e7be07a5b61e56b95589c96d6095e55daeea7b0a11d73eeddfbbb"],"state_sha256":"bfa73149d26178f13027a7e57a06d2b95ea2a8f8844694e80612c10f03987cdb"}