{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GLRR6RTOW5NUA4IDUQ57J5X2OK","short_pith_number":"pith:GLRR6RTO","schema_version":"1.0","canonical_sha256":"32e31f466eb75b407103a43bf4f6fa72977bad8bb30dbcba41e4836dd3cb01f7","source":{"kind":"arxiv","id":"2501.15217","version":1},"attestation_state":"computed","paper":{"title":"Predictive Lagrangian Optimization for Constrained Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Guojian Zhan, Jingliang Duan, Liping Zhang, Puzhen Yuan, Shengbo Eben Li, Tianqi Zhang, Yao Lyu, Zhenzhi Qin, Ziyu Lin","submitted_at":"2025-01-25T13:39:45Z","abstract_excerpt":"Constrained optimization is popularly seen in reinforcement learning for addressing complex control tasks. From the perspective of dynamic system, iteratively solving a constrained optimization problem can be framed as the temporal evolution of a feedback control system. Classical constrained optimization methods, such as penalty and Lagrangian approaches, inherently use proportional and integral feedback controllers. In this paper, we propose a more generic equivalence framework to build the connection between constrained optimization and feedback control system, for the purpose of developing"},"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":"2501.15217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T13:39:45Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"07e192c58a6e7128768e2c329a30f8b585f57b8ef0dbc074071dc7139edf9110","abstract_canon_sha256":"5c821d1ac04edce2db05069d02769415984b023c7dd598e2b8e9e3dcdb05ceff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:25.848310Z","signature_b64":"fsSfXKEBNbOsbvRCmFXIUWHYksbbrDDQyUio8f6Q56Kz247Yi/MWsYpkSNbwfp84juCKilo+m+7LUfbEqOvtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32e31f466eb75b407103a43bf4f6fa72977bad8bb30dbcba41e4836dd3cb01f7","last_reissued_at":"2026-07-05T10:05:25.847812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:25.847812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predictive Lagrangian Optimization for Constrained Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Guojian Zhan, Jingliang Duan, Liping Zhang, Puzhen Yuan, Shengbo Eben Li, Tianqi Zhang, Yao Lyu, Zhenzhi Qin, Ziyu Lin","submitted_at":"2025-01-25T13:39:45Z","abstract_excerpt":"Constrained optimization is popularly seen in reinforcement learning for addressing complex control tasks. From the perspective of dynamic system, iteratively solving a constrained optimization problem can be framed as the temporal evolution of a feedback control system. Classical constrained optimization methods, such as penalty and Lagrangian approaches, inherently use proportional and integral feedback controllers. In this paper, we propose a more generic equivalence framework to build the connection between constrained optimization and feedback control system, for the purpose of developing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15217","kind":"arxiv","version":1},"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/2501.15217/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":"2501.15217","created_at":"2026-07-05T10:05:25.847873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15217v1","created_at":"2026-07-05T10:05:25.847873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15217","created_at":"2026-07-05T10:05:25.847873+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLRR6RTOW5NU","created_at":"2026-07-05T10:05:25.847873+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLRR6RTOW5NUA4ID","created_at":"2026-07-05T10:05:25.847873+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLRR6RTO","created_at":"2026-07-05T10:05:25.847873+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/GLRR6RTOW5NUA4IDUQ57J5X2OK","json":"https://pith.science/pith/GLRR6RTOW5NUA4IDUQ57J5X2OK.json","graph_json":"https://pith.science/api/pith-number/GLRR6RTOW5NUA4IDUQ57J5X2OK/graph.json","events_json":"https://pith.science/api/pith-number/GLRR6RTOW5NUA4IDUQ57J5X2OK/events.json","paper":"https://pith.science/paper/GLRR6RTO"},"agent_actions":{"view_html":"https://pith.science/pith/GLRR6RTOW5NUA4IDUQ57J5X2OK","download_json":"https://pith.science/pith/GLRR6RTOW5NUA4IDUQ57J5X2OK.json","view_paper":"https://pith.science/paper/GLRR6RTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15217&json=true","fetch_graph":"https://pith.science/api/pith-number/GLRR6RTOW5NUA4IDUQ57J5X2OK/graph.json","fetch_events":"https://pith.science/api/pith-number/GLRR6RTOW5NUA4IDUQ57J5X2OK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLRR6RTOW5NUA4IDUQ57J5X2OK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLRR6RTOW5NUA4IDUQ57J5X2OK/action/storage_attestation","attest_author":"https://pith.science/pith/GLRR6RTOW5NUA4IDUQ57J5X2OK/action/author_attestation","sign_citation":"https://pith.science/pith/GLRR6RTOW5NUA4IDUQ57J5X2OK/action/citation_signature","submit_replication":"https://pith.science/pith/GLRR6RTOW5NUA4IDUQ57J5X2OK/action/replication_record"}},"created_at":"2026-07-05T10:05:25.847873+00:00","updated_at":"2026-07-05T10:05:25.847873+00:00"}