{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F5CL5ZK65JY42S6BS5N43D7CAN","short_pith_number":"pith:F5CL5ZK6","schema_version":"1.0","canonical_sha256":"2f44bee55eea71cd4bc1975bcd8fe203498c9f0e7fe09b6cbdb857c641ee2836","source":{"kind":"arxiv","id":"2503.06751","version":1},"attestation_state":"computed","paper":{"title":"Primal-Dual Sample Complexity Bounds for Constrained Markov Decision Processes with Multiple Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Spanopoulos, Konstantinos Papathanasiou, Max Buckley","submitted_at":"2025-03-09T20:10:35Z","abstract_excerpt":"This paper addresses the challenge of solving Constrained Markov Decision Processes (CMDPs) with $d > 1$ constraints when the transition dynamics are unknown, but samples can be drawn from a generative model. We propose a model-based algorithm for infinite horizon CMDPs with multiple constraints in the tabular setting, aiming to derive and prove sample complexity bounds for learning near-optimal policies. Our approach tackles both the relaxed and strict feasibility settings, where relaxed feasibility allows some constraint violations, and strict feasibility requires adherence to all constraint"},"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":"2503.06751","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-09T20:10:35Z","cross_cats_sorted":[],"title_canon_sha256":"4f4637fbbf3c6f0127f4a8de883dfc07174e444701f99f59948d1730b5a394ff","abstract_canon_sha256":"e3280b3e353dc077a5bd19897acec82b0a17f65258da048fb2fd6880fe39b935"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:41.470954Z","signature_b64":"wYfp3qnCvYJ0cnRjqLLQcgyaz27RtFemku7oBg66thXe2dATa7Rr6rMs/zZZldNWUvc9l2g57iJnx8oxYcRYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f44bee55eea71cd4bc1975bcd8fe203498c9f0e7fe09b6cbdb857c641ee2836","last_reissued_at":"2026-07-05T10:27:41.469862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:41.469862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Primal-Dual Sample Complexity Bounds for Constrained Markov Decision Processes with Multiple Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Spanopoulos, Konstantinos Papathanasiou, Max Buckley","submitted_at":"2025-03-09T20:10:35Z","abstract_excerpt":"This paper addresses the challenge of solving Constrained Markov Decision Processes (CMDPs) with $d > 1$ constraints when the transition dynamics are unknown, but samples can be drawn from a generative model. We propose a model-based algorithm for infinite horizon CMDPs with multiple constraints in the tabular setting, aiming to derive and prove sample complexity bounds for learning near-optimal policies. Our approach tackles both the relaxed and strict feasibility settings, where relaxed feasibility allows some constraint violations, and strict feasibility requires adherence to all constraint"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06751","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/2503.06751/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":"2503.06751","created_at":"2026-07-05T10:27:41.469970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06751v1","created_at":"2026-07-05T10:27:41.469970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06751","created_at":"2026-07-05T10:27:41.469970+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5CL5ZK65JY4","created_at":"2026-07-05T10:27:41.469970+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5CL5ZK65JY42S6B","created_at":"2026-07-05T10:27:41.469970+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5CL5ZK6","created_at":"2026-07-05T10:27:41.469970+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/F5CL5ZK65JY42S6BS5N43D7CAN","json":"https://pith.science/pith/F5CL5ZK65JY42S6BS5N43D7CAN.json","graph_json":"https://pith.science/api/pith-number/F5CL5ZK65JY42S6BS5N43D7CAN/graph.json","events_json":"https://pith.science/api/pith-number/F5CL5ZK65JY42S6BS5N43D7CAN/events.json","paper":"https://pith.science/paper/F5CL5ZK6"},"agent_actions":{"view_html":"https://pith.science/pith/F5CL5ZK65JY42S6BS5N43D7CAN","download_json":"https://pith.science/pith/F5CL5ZK65JY42S6BS5N43D7CAN.json","view_paper":"https://pith.science/paper/F5CL5ZK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06751&json=true","fetch_graph":"https://pith.science/api/pith-number/F5CL5ZK65JY42S6BS5N43D7CAN/graph.json","fetch_events":"https://pith.science/api/pith-number/F5CL5ZK65JY42S6BS5N43D7CAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5CL5ZK65JY42S6BS5N43D7CAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5CL5ZK65JY42S6BS5N43D7CAN/action/storage_attestation","attest_author":"https://pith.science/pith/F5CL5ZK65JY42S6BS5N43D7CAN/action/author_attestation","sign_citation":"https://pith.science/pith/F5CL5ZK65JY42S6BS5N43D7CAN/action/citation_signature","submit_replication":"https://pith.science/pith/F5CL5ZK65JY42S6BS5N43D7CAN/action/replication_record"}},"created_at":"2026-07-05T10:27:41.469970+00:00","updated_at":"2026-07-05T10:27:41.469970+00:00"}