{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W4625GTPIQ6UJRQGC6LS2FWEYF","short_pith_number":"pith:W4625GTP","schema_version":"1.0","canonical_sha256":"b73dae9a6f443d44c60617972d16c4c1564ebcd4fb1789164997629135ece1ee","source":{"kind":"arxiv","id":"2306.07001","version":2},"attestation_state":"computed","paper":{"title":"Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrian M\\\"uller, Giorgia Ramponi, Niao He, Pragnya Alatur","submitted_at":"2023-06-12T10:10:57Z","abstract_excerpt":"Constrained Markov Decision Processes (CMDPs) are one of the common ways to model safe reinforcement learning problems, where constraint functions model the safety objectives. Lagrangian-based dual or primal-dual algorithms provide efficient methods for learning in CMDPs. For these algorithms, the currently known regret bounds in the finite-horizon setting allow for a \"cancellation of errors\"; one can compensate for a constraint violation in one episode with a strict constraint satisfaction in another. However, we do not consider such a behavior safe in practical applications. In this paper, w"},"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":"2306.07001","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T10:10:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6770a2236b1eed017de294aeb487923490611f1868c9d32671c240e85b42d303","abstract_canon_sha256":"e9b10140910f19f1dd8b39221d829b2f7b202d388cebe256d390affefe498317"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:05.884689Z","signature_b64":"FZ2gpYD0I560HbY+irUEQ/SbCJJqJnmKutEBwLCFQ8ILopa+1NkwXkNHOPStWEoao1cNFyZIvznCOhLy+xM9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b73dae9a6f443d44c60617972d16c4c1564ebcd4fb1789164997629135ece1ee","last_reissued_at":"2026-07-05T06:46:05.884173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:05.884173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrian M\\\"uller, Giorgia Ramponi, Niao He, Pragnya Alatur","submitted_at":"2023-06-12T10:10:57Z","abstract_excerpt":"Constrained Markov Decision Processes (CMDPs) are one of the common ways to model safe reinforcement learning problems, where constraint functions model the safety objectives. Lagrangian-based dual or primal-dual algorithms provide efficient methods for learning in CMDPs. For these algorithms, the currently known regret bounds in the finite-horizon setting allow for a \"cancellation of errors\"; one can compensate for a constraint violation in one episode with a strict constraint satisfaction in another. However, we do not consider such a behavior safe in practical applications. In this paper, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07001","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/2306.07001/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":"2306.07001","created_at":"2026-07-05T06:46:05.884233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07001v2","created_at":"2026-07-05T06:46:05.884233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07001","created_at":"2026-07-05T06:46:05.884233+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4625GTPIQ6U","created_at":"2026-07-05T06:46:05.884233+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4625GTPIQ6UJRQG","created_at":"2026-07-05T06:46:05.884233+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4625GTP","created_at":"2026-07-05T06:46:05.884233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11694","citing_title":"Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11535","citing_title":"Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4625GTPIQ6UJRQGC6LS2FWEYF","json":"https://pith.science/pith/W4625GTPIQ6UJRQGC6LS2FWEYF.json","graph_json":"https://pith.science/api/pith-number/W4625GTPIQ6UJRQGC6LS2FWEYF/graph.json","events_json":"https://pith.science/api/pith-number/W4625GTPIQ6UJRQGC6LS2FWEYF/events.json","paper":"https://pith.science/paper/W4625GTP"},"agent_actions":{"view_html":"https://pith.science/pith/W4625GTPIQ6UJRQGC6LS2FWEYF","download_json":"https://pith.science/pith/W4625GTPIQ6UJRQGC6LS2FWEYF.json","view_paper":"https://pith.science/paper/W4625GTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07001&json=true","fetch_graph":"https://pith.science/api/pith-number/W4625GTPIQ6UJRQGC6LS2FWEYF/graph.json","fetch_events":"https://pith.science/api/pith-number/W4625GTPIQ6UJRQGC6LS2FWEYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4625GTPIQ6UJRQGC6LS2FWEYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4625GTPIQ6UJRQGC6LS2FWEYF/action/storage_attestation","attest_author":"https://pith.science/pith/W4625GTPIQ6UJRQGC6LS2FWEYF/action/author_attestation","sign_citation":"https://pith.science/pith/W4625GTPIQ6UJRQGC6LS2FWEYF/action/citation_signature","submit_replication":"https://pith.science/pith/W4625GTPIQ6UJRQGC6LS2FWEYF/action/replication_record"}},"created_at":"2026-07-05T06:46:05.884233+00:00","updated_at":"2026-07-05T06:46:05.884233+00:00"}