{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4KHGNROVHMETGHEBAPBH2IXCEO","short_pith_number":"pith:4KHGNROV","canonical_record":{"source":{"id":"1903.01004","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-03T22:24:01Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b1758505b4ba36ba14e1d48753cee54d6916f7ee467e092df64bd22fbf79e2f2","abstract_canon_sha256":"2055c57f9fb1beb5efdcda0f6f1dd2e30066560f09166872e1d06bff1c29c538"},"schema_version":"1.0"},"canonical_sha256":"e28e66c5d53b09331c8103c27d22e2239153a95909a0493d6364f712699a5945","source":{"kind":"arxiv","id":"1903.01004","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.01004","created_at":"2026-05-17T23:44:55Z"},{"alias_kind":"arxiv_version","alias_value":"1903.01004v3","created_at":"2026-05-17T23:44:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.01004","created_at":"2026-05-17T23:44:55Z"},{"alias_kind":"pith_short_12","alias_value":"4KHGNROVHMET","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4KHGNROVHMETGHEB","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4KHGNROV","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4KHGNROVHMETGHEBAPBH2IXCEO","target":"record","payload":{"canonical_record":{"source":{"id":"1903.01004","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-03T22:24:01Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b1758505b4ba36ba14e1d48753cee54d6916f7ee467e092df64bd22fbf79e2f2","abstract_canon_sha256":"2055c57f9fb1beb5efdcda0f6f1dd2e30066560f09166872e1d06bff1c29c538"},"schema_version":"1.0"},"canonical_sha256":"e28e66c5d53b09331c8103c27d22e2239153a95909a0493d6364f712699a5945","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:55.065900Z","signature_b64":"H8PoS6FDoCkqPb/DnXTzB+f7wkgZL61gPDSSm4sS+dMviYpAKQMoCwKVhvnhoe96IbbK81TEFKMP1PQ4GsTzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e28e66c5d53b09331c8103c27d22e2239153a95909a0493d6364f712699a5945","last_reissued_at":"2026-05-17T23:44:55.065211Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:55.065211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.01004","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":"2026-05-17T23:44:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CFXu6Vg7bHKcJgku3o8bht24wlGTIFCtCCFyEHRrnD5RDPpzPdcEzTpmmvyooSpzYt9oT14ZOGax/r0ScrqyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T00:19:17.928112Z"},"content_sha256":"e61038af4bea1e68c5bd0a2dee2cd35c4c6623ade1ca2a091bfb290a7bef731e","schema_version":"1.0","event_id":"sha256:e61038af4bea1e68c5bd0a2dee2cd35c4c6623ade1ca2a091bfb290a7bef731e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4KHGNROVHMETGHEBAPBH2IXCEO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Budgeted Reinforcement Learning in Continuous State Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Edouard Leurent, Nicolas Carrara, Odalric-Ambrym Maillard, Olivier Pietquin, Romain Laroche, Tanguy Urvoy","submitted_at":"2019-03-03T22:24:01Z","abstract_excerpt":"A Budgeted Markov Decision Process (BMDP) is an extension of a Markov Decision Process to critical applications requiring safety constraints. It relies on a notion of risk implemented in the shape of a cost signal constrained to lie below an - adjustable - threshold. So far, BMDPs could only be solved in the case of finite state spaces with known dynamics. This work extends the state-of-the-art to continuous spaces environments and unknown dynamics. We show that the solution to a BMDP is a fixed point of a novel Budgeted Bellman Optimality operator. This observation allows us to introduce natu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.01004","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":"2026-05-17T23:44:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I+w3aVGXzaocfE+R9za7HX2/o+VTB0LItK+jER95LAbeetSbtk9Ixu/SyKoUUN1Wg3mLE/sop36um5xx1bzeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T00:19:17.928515Z"},"content_sha256":"ea296540b346ee685841256dc7c84ab246415018fafca4ed6828a43c843ff8d7","schema_version":"1.0","event_id":"sha256:ea296540b346ee685841256dc7c84ab246415018fafca4ed6828a43c843ff8d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO/bundle.json","state_url":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4KHGNROVHMETGHEBAPBH2IXCEO/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":"2026-05-23T00:19:17Z","links":{"resolver":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO","bundle":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO/bundle.json","state":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4KHGNROVHMETGHEBAPBH2IXCEO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4KHGNROVHMETGHEBAPBH2IXCEO","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":"2055c57f9fb1beb5efdcda0f6f1dd2e30066560f09166872e1d06bff1c29c538","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-03T22:24:01Z","title_canon_sha256":"b1758505b4ba36ba14e1d48753cee54d6916f7ee467e092df64bd22fbf79e2f2"},"schema_version":"1.0","source":{"id":"1903.01004","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.01004","created_at":"2026-05-17T23:44:55Z"},{"alias_kind":"arxiv_version","alias_value":"1903.01004v3","created_at":"2026-05-17T23:44:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.01004","created_at":"2026-05-17T23:44:55Z"},{"alias_kind":"pith_short_12","alias_value":"4KHGNROVHMET","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4KHGNROVHMETGHEB","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4KHGNROV","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:ea296540b346ee685841256dc7c84ab246415018fafca4ed6828a43c843ff8d7","target":"graph","created_at":"2026-05-17T23:44:55Z","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":"A Budgeted Markov Decision Process (BMDP) is an extension of a Markov Decision Process to critical applications requiring safety constraints. It relies on a notion of risk implemented in the shape of a cost signal constrained to lie below an - adjustable - threshold. So far, BMDPs could only be solved in the case of finite state spaces with known dynamics. This work extends the state-of-the-art to continuous spaces environments and unknown dynamics. We show that the solution to a BMDP is a fixed point of a novel Budgeted Bellman Optimality operator. This observation allows us to introduce natu","authors_text":"Edouard Leurent, Nicolas Carrara, Odalric-Ambrym Maillard, Olivier Pietquin, Romain Laroche, Tanguy Urvoy","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-03T22:24:01Z","title":"Budgeted Reinforcement Learning in Continuous State Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.01004","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:e61038af4bea1e68c5bd0a2dee2cd35c4c6623ade1ca2a091bfb290a7bef731e","target":"record","created_at":"2026-05-17T23:44:55Z","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":"2055c57f9fb1beb5efdcda0f6f1dd2e30066560f09166872e1d06bff1c29c538","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-03T22:24:01Z","title_canon_sha256":"b1758505b4ba36ba14e1d48753cee54d6916f7ee467e092df64bd22fbf79e2f2"},"schema_version":"1.0","source":{"id":"1903.01004","kind":"arxiv","version":3}},"canonical_sha256":"e28e66c5d53b09331c8103c27d22e2239153a95909a0493d6364f712699a5945","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e28e66c5d53b09331c8103c27d22e2239153a95909a0493d6364f712699a5945","first_computed_at":"2026-05-17T23:44:55.065211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:55.065211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H8PoS6FDoCkqPb/DnXTzB+f7wkgZL61gPDSSm4sS+dMviYpAKQMoCwKVhvnhoe96IbbK81TEFKMP1PQ4GsTzAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:55.065900Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.01004","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e61038af4bea1e68c5bd0a2dee2cd35c4c6623ade1ca2a091bfb290a7bef731e","sha256:ea296540b346ee685841256dc7c84ab246415018fafca4ed6828a43c843ff8d7"],"state_sha256":"0ac118d7b93970c721c1468484c64593b9e0fad059659ff659ee1007d81f1e4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N4wWIkluOZ0YHZeuwWKeNq6NaDt99hJ+mDw//kOEkVp5fCiXlENbpD32GEHVY+38y2wKTTFtlWRnR5Pgint/Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T00:19:17.931305Z","bundle_sha256":"1356d8fcedc7b7af80ddc0c8cfee1ebb06580918b5ba7266a4daac13f2a2da14"}}