{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EPDCMMR6PUDDNH4FNCUSLD7F4E","short_pith_number":"pith:EPDCMMR6","schema_version":"1.0","canonical_sha256":"23c626323e7d06369f8568a9258fe5e10a5e0cdbf9785d44677df197069a1323","source":{"kind":"arxiv","id":"2504.00626","version":2},"attestation_state":"computed","paper":{"title":"Probabilistically safe and efficient model-based reinforcement learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Azita Dabiri, Bart De Schutter, Filippo Airaldi","submitted_at":"2025-04-01T10:24:54Z","abstract_excerpt":"This paper proposes tackling safety-critical stochastic Reinforcement Learning (RL) tasks with a sample-based, model-based approach. At the core of the method lies a Model Predictive Control (MPC) scheme that acts as function approximation, providing a model-based predictive control policy. To ensure safety, a probabilistic Control Barrier Function (CBF) is integrated into the MPC controller. To approximate the effects of stochasticies in the optimal control formulation and to fulfil the probabilistic CBF condition, a sample-based approach with guarantees is employed. Furthermore, to counterba"},"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":"2504.00626","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-04-01T10:24:54Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"3831853accf70cbc06703ee3f7752744575fc219384bc68ae8d71247af6987b2","abstract_canon_sha256":"e21cf8977bb5e72eeadb8cd1713781decd61d897574038d33a2f0bd6f5286511"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:47.400812Z","signature_b64":"OxL4FD28/ZTxt9qbwJjgTb60t65+vx/o/+TtRfJH1Dd1KHovukJK19PJRy/Mtjymo7leb5z6fnYvAcnps+q7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23c626323e7d06369f8568a9258fe5e10a5e0cdbf9785d44677df197069a1323","last_reissued_at":"2026-07-05T11:44:47.400162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:47.400162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistically safe and efficient model-based reinforcement learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Azita Dabiri, Bart De Schutter, Filippo Airaldi","submitted_at":"2025-04-01T10:24:54Z","abstract_excerpt":"This paper proposes tackling safety-critical stochastic Reinforcement Learning (RL) tasks with a sample-based, model-based approach. At the core of the method lies a Model Predictive Control (MPC) scheme that acts as function approximation, providing a model-based predictive control policy. To ensure safety, a probabilistic Control Barrier Function (CBF) is integrated into the MPC controller. To approximate the effects of stochasticies in the optimal control formulation and to fulfil the probabilistic CBF condition, a sample-based approach with guarantees is employed. Furthermore, to counterba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00626","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.00626/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2504.00626","created_at":"2026-07-05T11:44:47.400232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00626v2","created_at":"2026-07-05T11:44:47.400232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00626","created_at":"2026-07-05T11:44:47.400232+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPDCMMR6PUDD","created_at":"2026-07-05T11:44:47.400232+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPDCMMR6PUDDNH4F","created_at":"2026-07-05T11:44:47.400232+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPDCMMR6","created_at":"2026-07-05T11:44:47.400232+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/EPDCMMR6PUDDNH4FNCUSLD7F4E","json":"https://pith.science/pith/EPDCMMR6PUDDNH4FNCUSLD7F4E.json","graph_json":"https://pith.science/api/pith-number/EPDCMMR6PUDDNH4FNCUSLD7F4E/graph.json","events_json":"https://pith.science/api/pith-number/EPDCMMR6PUDDNH4FNCUSLD7F4E/events.json","paper":"https://pith.science/paper/EPDCMMR6"},"agent_actions":{"view_html":"https://pith.science/pith/EPDCMMR6PUDDNH4FNCUSLD7F4E","download_json":"https://pith.science/pith/EPDCMMR6PUDDNH4FNCUSLD7F4E.json","view_paper":"https://pith.science/paper/EPDCMMR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00626&json=true","fetch_graph":"https://pith.science/api/pith-number/EPDCMMR6PUDDNH4FNCUSLD7F4E/graph.json","fetch_events":"https://pith.science/api/pith-number/EPDCMMR6PUDDNH4FNCUSLD7F4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPDCMMR6PUDDNH4FNCUSLD7F4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPDCMMR6PUDDNH4FNCUSLD7F4E/action/storage_attestation","attest_author":"https://pith.science/pith/EPDCMMR6PUDDNH4FNCUSLD7F4E/action/author_attestation","sign_citation":"https://pith.science/pith/EPDCMMR6PUDDNH4FNCUSLD7F4E/action/citation_signature","submit_replication":"https://pith.science/pith/EPDCMMR6PUDDNH4FNCUSLD7F4E/action/replication_record"}},"created_at":"2026-07-05T11:44:47.400232+00:00","updated_at":"2026-07-05T11:44:47.400232+00:00"}