{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V4TXID5AZQHFHBF77K5ORD3WKO","short_pith_number":"pith:V4TXID5A","schema_version":"1.0","canonical_sha256":"af27740fa0cc0e5384bffabae88f765382ba03532db184eb31491a864c703e3a","source":{"kind":"arxiv","id":"2511.15053","version":2},"attestation_state":"computed","paper":{"title":"Distributed primal-dual algorithm for constrained multi-agent reinforcement learning under coupled policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Dongming Wang, He Wang, Pengcheng Dai, Wenwu Yu","submitted_at":"2025-11-19T02:46:26Z","abstract_excerpt":"This paper investigates constrained multi-agent reinforcement learning (CMARL) in coupled environments, where agents collaboratively maximize the sum of local objectives while satisfying individual safety constraints. Existing studies face two limitations: (1) most rely on independent policies that fail to capture complex interactions in coupled environments; and (2) agents require the global Lagrange multipliers, which are sensitive learned variables whose global sharing risks exposing private agent-specific information. To overcome these issues, we propose a framework where agents adopt coup"},"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":"2511.15053","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-11-19T02:46:26Z","cross_cats_sorted":[],"title_canon_sha256":"60c77e51b9337e5f9952012b822e813f7a0a50eb02e97a09458b91a061925997","abstract_canon_sha256":"4c06c622b99465c3a2fcc4160b4a82591ad8b145ade339030dacd12c58fbb0ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:01.830051Z","signature_b64":"BvGHPprgXEE0MHIqBtWaILwXEKW0jnkenTjGWTdcmRC/qDjtXl0RfMTG2WP/ILnqPKH8tf/peqiOpvR/N0DfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af27740fa0cc0e5384bffabae88f765382ba03532db184eb31491a864c703e3a","last_reissued_at":"2026-07-24T01:23:01.829057Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:01.829057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed primal-dual algorithm for constrained multi-agent reinforcement learning under coupled policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Dongming Wang, He Wang, Pengcheng Dai, Wenwu Yu","submitted_at":"2025-11-19T02:46:26Z","abstract_excerpt":"This paper investigates constrained multi-agent reinforcement learning (CMARL) in coupled environments, where agents collaboratively maximize the sum of local objectives while satisfying individual safety constraints. Existing studies face two limitations: (1) most rely on independent policies that fail to capture complex interactions in coupled environments; and (2) agents require the global Lagrange multipliers, which are sensitive learned variables whose global sharing risks exposing private agent-specific information. To overcome these issues, we propose a framework where agents adopt coup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.15053","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/2511.15053/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":"2511.15053","created_at":"2026-07-24T01:23:01.829527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.15053v2","created_at":"2026-07-24T01:23:01.829527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.15053","created_at":"2026-07-24T01:23:01.829527+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4TXID5AZQHF","created_at":"2026-07-24T01:23:01.829527+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4TXID5AZQHFHBF7","created_at":"2026-07-24T01:23:01.829527+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4TXID5A","created_at":"2026-07-24T01:23:01.829527+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/V4TXID5AZQHFHBF77K5ORD3WKO","json":"https://pith.science/pith/V4TXID5AZQHFHBF77K5ORD3WKO.json","graph_json":"https://pith.science/api/pith-number/V4TXID5AZQHFHBF77K5ORD3WKO/graph.json","events_json":"https://pith.science/api/pith-number/V4TXID5AZQHFHBF77K5ORD3WKO/events.json","paper":"https://pith.science/paper/V4TXID5A"},"agent_actions":{"view_html":"https://pith.science/pith/V4TXID5AZQHFHBF77K5ORD3WKO","download_json":"https://pith.science/pith/V4TXID5AZQHFHBF77K5ORD3WKO.json","view_paper":"https://pith.science/paper/V4TXID5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.15053&json=true","fetch_graph":"https://pith.science/api/pith-number/V4TXID5AZQHFHBF77K5ORD3WKO/graph.json","fetch_events":"https://pith.science/api/pith-number/V4TXID5AZQHFHBF77K5ORD3WKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4TXID5AZQHFHBF77K5ORD3WKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4TXID5AZQHFHBF77K5ORD3WKO/action/storage_attestation","attest_author":"https://pith.science/pith/V4TXID5AZQHFHBF77K5ORD3WKO/action/author_attestation","sign_citation":"https://pith.science/pith/V4TXID5AZQHFHBF77K5ORD3WKO/action/citation_signature","submit_replication":"https://pith.science/pith/V4TXID5AZQHFHBF77K5ORD3WKO/action/replication_record"}},"created_at":"2026-07-24T01:23:01.829527+00:00","updated_at":"2026-07-24T01:23:01.829527+00:00"}