{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:BX2B4SDZCZJUT3SOBXJ2KBTS6Y","short_pith_number":"pith:BX2B4SDZ","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"},"canonical_sha256":"0df41e4879165349ee4e0dd3a50672f6307deec48b18f3f0ff4a39e418ac4a56","source":{"kind":"arxiv","id":"1512.01629","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:BX2B4SDZCZJUT3SOBXJ2KBTS6Y","target":"record","payload":{"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"},"canonical_sha256":"0df41e4879165349ee4e0dd3a50672f6307deec48b18f3f0ff4a39e418ac4a56","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"},"source_kind":"arxiv","source_id":"1512.01629","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NZJikTC4/sFDVAnVGOp/egc6TYi15qHuqIXg+WVlRE9kgEGeCMMOShd+9r04OyBB/Uhw9t+a5tbDAM2n9es4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T16:08:22.466837Z"},"content_sha256":"42ae9fbb52cb67592d99bce875ef5af4f7fe481705b17ea8e3a130cfcca8f9a7","schema_version":"1.0","event_id":"sha256:42ae9fbb52cb67592d99bce875ef5af4f7fe481705b17ea8e3a130cfcca8f9a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:BX2B4SDZCZJUT3SOBXJ2KBTS6Y","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EmN+uu7UFNWOq2NWxOD6vO/SPLEnjAr2YqjksVMHZiPp2G/vuDb3SmXOW1/bYU1816gcqOQfIoysR5hFDhR/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T16:08:22.467180Z"},"content_sha256":"36ba644c7c0e7be07a5b61e56b95589c96d6095e55daeea7b0a11d73eeddfbbb","schema_version":"1.0","event_id":"sha256:36ba644c7c0e7be07a5b61e56b95589c96d6095e55daeea7b0a11d73eeddfbbb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/bundle.json","state_url":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T16:08:22Z","links":{"resolver":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y","bundle":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/bundle.json","state":"https://pith.science/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BX2B4SDZCZJUT3SOBXJ2KBTS6Y/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jPezD9ftPdjxWLI8TU3Gw1YXmyDt/jB7TuSjuoG3ndUQseHBvjKNmY5prFYR1CLsvS0oXDzYu8G6+46dzxJyAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T16:08:22.469221Z","bundle_sha256":"547cc47be28aff774f228f4bccc24521adc2f2ad693ad3083b6d2ebd4c6d9630"}}