{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I4HYREWYBZNT7KDDBCPOUZGDQF","short_pith_number":"pith:I4HYREWY","schema_version":"1.0","canonical_sha256":"470f8892d80e5b3fa863089eea64c38171eb40520e4170bc2611b6c9ea676861","source":{"kind":"arxiv","id":"2502.16496","version":1},"attestation_state":"computed","paper":{"title":"PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Kun Hu, Minglong Li, Minne Li, Muning Wen, Shao Zhang, Xihuai Wang, Ying Wen, Yiwei Shi","submitted_at":"2025-02-23T08:30:14Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) faces challenges in coordinating agents due to complex interdependencies within multi-agent systems. Most MARL algorithms use the simultaneous decision-making paradigm but ignore the action-level dependencies among agents, which reduces coordination efficiency. In contrast, the sequential decision-making paradigm provides finer-grained supervision for agent decision order, presenting the potential for handling dependencies via better decision order management. However, determining the optimal decision order remains a challenge. In this paper, we introd"},"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":"2502.16496","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-23T08:30:14Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"b35e55945d6d0b5426a800de434e23790cc244231006ea260cdded80299275bf","abstract_canon_sha256":"349ba31d98c24efab2b4c2d330315c99b3e3641afc27b38a7c967f845ff6e09f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:54.324696Z","signature_b64":"2JiWzHgQshG7YqrgI6wSwGj3bokd5ptNHWIuuB7sfqxUVVfKBogA3CMZVyBTgv0i4t+6YKM2oU6Do/YxjulwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"470f8892d80e5b3fa863089eea64c38171eb40520e4170bc2611b6c9ea676861","last_reissued_at":"2026-07-05T10:18:54.324245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:54.324245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Kun Hu, Minglong Li, Minne Li, Muning Wen, Shao Zhang, Xihuai Wang, Ying Wen, Yiwei Shi","submitted_at":"2025-02-23T08:30:14Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) faces challenges in coordinating agents due to complex interdependencies within multi-agent systems. Most MARL algorithms use the simultaneous decision-making paradigm but ignore the action-level dependencies among agents, which reduces coordination efficiency. In contrast, the sequential decision-making paradigm provides finer-grained supervision for agent decision order, presenting the potential for handling dependencies via better decision order management. However, determining the optimal decision order remains a challenge. In this paper, we introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16496","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/2502.16496/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":"2502.16496","created_at":"2026-07-05T10:18:54.324321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16496v1","created_at":"2026-07-05T10:18:54.324321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16496","created_at":"2026-07-05T10:18:54.324321+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4HYREWYBZNT","created_at":"2026-07-05T10:18:54.324321+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4HYREWYBZNT7KDD","created_at":"2026-07-05T10:18:54.324321+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4HYREWY","created_at":"2026-07-05T10:18:54.324321+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/I4HYREWYBZNT7KDDBCPOUZGDQF","json":"https://pith.science/pith/I4HYREWYBZNT7KDDBCPOUZGDQF.json","graph_json":"https://pith.science/api/pith-number/I4HYREWYBZNT7KDDBCPOUZGDQF/graph.json","events_json":"https://pith.science/api/pith-number/I4HYREWYBZNT7KDDBCPOUZGDQF/events.json","paper":"https://pith.science/paper/I4HYREWY"},"agent_actions":{"view_html":"https://pith.science/pith/I4HYREWYBZNT7KDDBCPOUZGDQF","download_json":"https://pith.science/pith/I4HYREWYBZNT7KDDBCPOUZGDQF.json","view_paper":"https://pith.science/paper/I4HYREWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16496&json=true","fetch_graph":"https://pith.science/api/pith-number/I4HYREWYBZNT7KDDBCPOUZGDQF/graph.json","fetch_events":"https://pith.science/api/pith-number/I4HYREWYBZNT7KDDBCPOUZGDQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4HYREWYBZNT7KDDBCPOUZGDQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4HYREWYBZNT7KDDBCPOUZGDQF/action/storage_attestation","attest_author":"https://pith.science/pith/I4HYREWYBZNT7KDDBCPOUZGDQF/action/author_attestation","sign_citation":"https://pith.science/pith/I4HYREWYBZNT7KDDBCPOUZGDQF/action/citation_signature","submit_replication":"https://pith.science/pith/I4HYREWYBZNT7KDDBCPOUZGDQF/action/replication_record"}},"created_at":"2026-07-05T10:18:54.324321+00:00","updated_at":"2026-07-05T10:18:54.324321+00:00"}