{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LOPRAVHX4XHWPHGMTRTSCBEQVG","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":"6b9c8c908209005f4e17fa16973174fa0aa6bf289764b4030f158d2163900dab","cross_cats_sorted":["cs.AI","cs.LG","cs.RO","cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-02-23T08:58:38Z","title_canon_sha256":"7191e73daf4a0abc1069b043f521c89f59ff2d08995d97882f015baa79b4254e"},"schema_version":"1.0","source":{"id":"2402.15197","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15197","created_at":"2026-07-05T08:54:47Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15197v1","created_at":"2026-07-05T08:54:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15197","created_at":"2026-07-05T08:54:47Z"},{"alias_kind":"pith_short_12","alias_value":"LOPRAVHX4XHW","created_at":"2026-07-05T08:54:47Z"},{"alias_kind":"pith_short_16","alias_value":"LOPRAVHX4XHWPHGM","created_at":"2026-07-05T08:54:47Z"},{"alias_kind":"pith_short_8","alias_value":"LOPRAVHX","created_at":"2026-07-05T08:54:47Z"}],"graph_snapshots":[{"event_id":"sha256:6c4a15d7fccb19e6065bb982cb0df72f8802844588dd52e7d614ed6e7478137e","target":"graph","created_at":"2026-07-05T08:54:47Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.15197/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe reinforcement learning (Safe RL) refers to a class of techniques that aim to prevent RL algorithms from violating constraints in the process of decision-making and exploration during trial and error. In this paper, a novel model-free Safe RL algorithm, formulated based on the multi-objective policy optimization framework is introduced where the policy is optimized towards optimality and safety, simultaneously. The optimality is achieved by the environment reward function that is subsequently shaped using a safety critic. The advantage of the Safety Optimized RL (SORL) algorithm compared t","authors_text":"Homayoun Honari, Homayoun Najjaran, Mehran Ghafarian Tamizi","cross_cats":["cs.AI","cs.LG","cs.RO","cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-02-23T08:58:38Z","title":"Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15197","kind":"arxiv","version":1},"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":"sha256:1f0991c8b37ad227bf4ec14c813c16b8f18fec9d7f7695902e871ea331443c82","target":"record","created_at":"2026-07-05T08:54:47Z","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":"6b9c8c908209005f4e17fa16973174fa0aa6bf289764b4030f158d2163900dab","cross_cats_sorted":["cs.AI","cs.LG","cs.RO","cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-02-23T08:58:38Z","title_canon_sha256":"7191e73daf4a0abc1069b043f521c89f59ff2d08995d97882f015baa79b4254e"},"schema_version":"1.0","source":{"id":"2402.15197","kind":"arxiv","version":1}},"canonical_sha256":"5b9f1054f7e5cf679ccc9c67210490a98cf7d8c572756e8d1664cb7bf93df85c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b9f1054f7e5cf679ccc9c67210490a98cf7d8c572756e8d1664cb7bf93df85c","first_computed_at":"2026-07-05T08:54:47.633247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:47.633247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mcmjoGWn1qYKY+dIgaxHRwMzDwQUzvYaJ69hEKggCJ8DtLdmUsCkdFzu0ekHAbXXkKOjKBdLFtzv1ousm1NtAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:47.633804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15197","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f0991c8b37ad227bf4ec14c813c16b8f18fec9d7f7695902e871ea331443c82","sha256:6c4a15d7fccb19e6065bb982cb0df72f8802844588dd52e7d614ed6e7478137e"],"state_sha256":"c1215db8987f550e71d52e8c1658263bf1490cc9a56e1596411043cf24ad532d"}