{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4KHGNROVHMETGHEBAPBH2IXCEO","short_pith_number":"pith:4KHGNROV","schema_version":"1.0","canonical_sha256":"e28e66c5d53b09331c8103c27d22e2239153a95909a0493d6364f712699a5945","source":{"kind":"arxiv","id":"1903.01004","version":3},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1903.01004","created_at":"2026-05-17T23:44:55.065305+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.01004v3","created_at":"2026-05-17T23:44:55.065305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.01004","created_at":"2026-05-17T23:44:55.065305+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KHGNROVHMET","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KHGNROVHMETGHEB","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KHGNROV","created_at":"2026-05-18T12:33:10.108867+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/4KHGNROVHMETGHEBAPBH2IXCEO","json":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO.json","graph_json":"https://pith.science/api/pith-number/4KHGNROVHMETGHEBAPBH2IXCEO/graph.json","events_json":"https://pith.science/api/pith-number/4KHGNROVHMETGHEBAPBH2IXCEO/events.json","paper":"https://pith.science/paper/4KHGNROV"},"agent_actions":{"view_html":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO","download_json":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO.json","view_paper":"https://pith.science/paper/4KHGNROV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.01004&json=true","fetch_graph":"https://pith.science/api/pith-number/4KHGNROVHMETGHEBAPBH2IXCEO/graph.json","fetch_events":"https://pith.science/api/pith-number/4KHGNROVHMETGHEBAPBH2IXCEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO/action/storage_attestation","attest_author":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO/action/author_attestation","sign_citation":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO/action/citation_signature","submit_replication":"https://pith.science/pith/4KHGNROVHMETGHEBAPBH2IXCEO/action/replication_record"}},"created_at":"2026-05-17T23:44:55.065305+00:00","updated_at":"2026-05-17T23:44:55.065305+00:00"}