{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7YMIYPI2VU65YY5NUCI67ZWSMW","short_pith_number":"pith:7YMIYPI2","schema_version":"1.0","canonical_sha256":"fe188c3d1aad3ddc63ada091efe6d265b502cd13a949f20ef685b7cb85f6b8ae","source":{"kind":"arxiv","id":"2205.14953","version":3},"attestation_state":"computed","paper":{"title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Jakub Grudzien Kuba, Jun Wang, Muning Wen, Runji Lin, Weinan Zhang, Yaodong Yang, Ying Wen","submitted_at":"2022-05-30T09:39:45Z","abstract_excerpt":"Large sequence model (SM) such as GPT series and BERT has displayed outstanding performance and generalization capabilities on vision, language, and recently reinforcement learning tasks. A natural follow-up question is how to abstract multi-agent decision making into an SM problem and benefit from the prosperous development of SMs. In this paper, we introduce a novel architecture named Multi-Agent Transformer (MAT) that effectively casts cooperative multi-agent reinforcement learning (MARL) into SM problems wherein the task is to map agents' observation sequence to agents' optimal action sequ"},"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":"2205.14953","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2022-05-30T09:39:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"67c7a2ad79c85d528d9c1acedae1295271d0a0f3a5064ee1cea859110d56ea1f","abstract_canon_sha256":"b0f8fc7e48bb1749e4f99819c4a054de0db85d2c64b7bea785786d78d6b4c085"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:22.267739Z","signature_b64":"/nb31YFjzZL54uUH1NWyzoZNk3hYqIiHinGKAG+dx/G3sA9Opf6qaZLRgxXa+9BCJ/8N6FEoP8zDXLOmkNj9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe188c3d1aad3ddc63ada091efe6d265b502cd13a949f20ef685b7cb85f6b8ae","last_reissued_at":"2026-07-05T05:11:22.267239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:22.267239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Jakub Grudzien Kuba, Jun Wang, Muning Wen, Runji Lin, Weinan Zhang, Yaodong Yang, Ying Wen","submitted_at":"2022-05-30T09:39:45Z","abstract_excerpt":"Large sequence model (SM) such as GPT series and BERT has displayed outstanding performance and generalization capabilities on vision, language, and recently reinforcement learning tasks. A natural follow-up question is how to abstract multi-agent decision making into an SM problem and benefit from the prosperous development of SMs. In this paper, we introduce a novel architecture named Multi-Agent Transformer (MAT) that effectively casts cooperative multi-agent reinforcement learning (MARL) into SM problems wherein the task is to map agents' observation sequence to agents' optimal action sequ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14953","kind":"arxiv","version":3},"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/2205.14953/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":"2205.14953","created_at":"2026-07-05T05:11:22.267295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14953v3","created_at":"2026-07-05T05:11:22.267295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14953","created_at":"2026-07-05T05:11:22.267295+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YMIYPI2VU65","created_at":"2026-07-05T05:11:22.267295+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YMIYPI2VU65YY5N","created_at":"2026-07-05T05:11:22.267295+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YMIYPI2","created_at":"2026-07-05T05:11:22.267295+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/7YMIYPI2VU65YY5NUCI67ZWSMW","json":"https://pith.science/pith/7YMIYPI2VU65YY5NUCI67ZWSMW.json","graph_json":"https://pith.science/api/pith-number/7YMIYPI2VU65YY5NUCI67ZWSMW/graph.json","events_json":"https://pith.science/api/pith-number/7YMIYPI2VU65YY5NUCI67ZWSMW/events.json","paper":"https://pith.science/paper/7YMIYPI2"},"agent_actions":{"view_html":"https://pith.science/pith/7YMIYPI2VU65YY5NUCI67ZWSMW","download_json":"https://pith.science/pith/7YMIYPI2VU65YY5NUCI67ZWSMW.json","view_paper":"https://pith.science/paper/7YMIYPI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14953&json=true","fetch_graph":"https://pith.science/api/pith-number/7YMIYPI2VU65YY5NUCI67ZWSMW/graph.json","fetch_events":"https://pith.science/api/pith-number/7YMIYPI2VU65YY5NUCI67ZWSMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YMIYPI2VU65YY5NUCI67ZWSMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YMIYPI2VU65YY5NUCI67ZWSMW/action/storage_attestation","attest_author":"https://pith.science/pith/7YMIYPI2VU65YY5NUCI67ZWSMW/action/author_attestation","sign_citation":"https://pith.science/pith/7YMIYPI2VU65YY5NUCI67ZWSMW/action/citation_signature","submit_replication":"https://pith.science/pith/7YMIYPI2VU65YY5NUCI67ZWSMW/action/replication_record"}},"created_at":"2026-07-05T05:11:22.267295+00:00","updated_at":"2026-07-05T05:11:22.267295+00:00"}