{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V7GUTC5DB76BSGFBK2CIZGHY7O","short_pith_number":"pith:V7GUTC5D","schema_version":"1.0","canonical_sha256":"afcd498ba30ffc1918a156848c98f8fb81a3cea1b7bf83d0a20ab7af3041bec8","source":{"kind":"arxiv","id":"2302.06205","version":2},"attestation_state":"computed","paper":{"title":"Order Matters: Agent-by-agent Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Jun Wang, Weinan Zhang, Xihuai Wang, Ying Wen, Zheng Tian, Ziyu Wan","submitted_at":"2023-02-13T09:24:34Z","abstract_excerpt":"While multi-agent trust region algorithms have achieved great success empirically in solving coordination tasks, most of them, however, suffer from a non-stationarity problem since agents update their policies simultaneously. In contrast, a sequential scheme that updates policies agent-by-agent provides another perspective and shows strong performance. However, sample inefficiency and lack of monotonic improvement guarantees for each agent are still the two significant challenges for the sequential scheme. In this paper, we propose the \\textbf{A}gent-by-\\textbf{a}gent \\textbf{P}olicy \\textbf{O"},"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":"2302.06205","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-13T09:24:34Z","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"title_canon_sha256":"838e5c6e19fdb4cc489a509db4920b64e8b7a5d296b8f9307aeaafe584f3b347","abstract_canon_sha256":"7ab24e7417f00f0034561238e9caf7b92f9699564859eb74c385bee1a5640ca0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:38.695489Z","signature_b64":"shTa6uQzWFIAF34HAIw7yL8YvWBX/dbkRYnzyKG/FpTmdnAR5tjkyHCY5BEVLwhqGTKN5bzuLtZA8IDEOGszBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afcd498ba30ffc1918a156848c98f8fb81a3cea1b7bf83d0a20ab7af3041bec8","last_reissued_at":"2026-07-05T05:45:38.695001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:38.695001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Order Matters: Agent-by-agent Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Jun Wang, Weinan Zhang, Xihuai Wang, Ying Wen, Zheng Tian, Ziyu Wan","submitted_at":"2023-02-13T09:24:34Z","abstract_excerpt":"While multi-agent trust region algorithms have achieved great success empirically in solving coordination tasks, most of them, however, suffer from a non-stationarity problem since agents update their policies simultaneously. In contrast, a sequential scheme that updates policies agent-by-agent provides another perspective and shows strong performance. However, sample inefficiency and lack of monotonic improvement guarantees for each agent are still the two significant challenges for the sequential scheme. In this paper, we propose the \\textbf{A}gent-by-\\textbf{a}gent \\textbf{P}olicy \\textbf{O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06205","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/2302.06205/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":"2302.06205","created_at":"2026-07-05T05:45:38.695072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06205v2","created_at":"2026-07-05T05:45:38.695072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06205","created_at":"2026-07-05T05:45:38.695072+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7GUTC5DB76B","created_at":"2026-07-05T05:45:38.695072+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7GUTC5DB76BSGFB","created_at":"2026-07-05T05:45:38.695072+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7GUTC5D","created_at":"2026-07-05T05:45:38.695072+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/V7GUTC5DB76BSGFBK2CIZGHY7O","json":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O.json","graph_json":"https://pith.science/api/pith-number/V7GUTC5DB76BSGFBK2CIZGHY7O/graph.json","events_json":"https://pith.science/api/pith-number/V7GUTC5DB76BSGFBK2CIZGHY7O/events.json","paper":"https://pith.science/paper/V7GUTC5D"},"agent_actions":{"view_html":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O","download_json":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O.json","view_paper":"https://pith.science/paper/V7GUTC5D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06205&json=true","fetch_graph":"https://pith.science/api/pith-number/V7GUTC5DB76BSGFBK2CIZGHY7O/graph.json","fetch_events":"https://pith.science/api/pith-number/V7GUTC5DB76BSGFBK2CIZGHY7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O/action/storage_attestation","attest_author":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O/action/author_attestation","sign_citation":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O/action/citation_signature","submit_replication":"https://pith.science/pith/V7GUTC5DB76BSGFBK2CIZGHY7O/action/replication_record"}},"created_at":"2026-07-05T05:45:38.695072+00:00","updated_at":"2026-07-05T05:45:38.695072+00:00"}