{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7YMIYPI2VU65YY5NUCI67ZWSMW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b0f8fc7e48bb1749e4f99819c4a054de0db85d2c64b7bea785786d78d6b4c085","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2022-05-30T09:39:45Z","title_canon_sha256":"67c7a2ad79c85d528d9c1acedae1295271d0a0f3a5064ee1cea859110d56ea1f"},"schema_version":"1.0","source":{"id":"2205.14953","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14953","created_at":"2026-07-05T05:11:22Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14953v3","created_at":"2026-07-05T05:11:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14953","created_at":"2026-07-05T05:11:22Z"},{"alias_kind":"pith_short_12","alias_value":"7YMIYPI2VU65","created_at":"2026-07-05T05:11:22Z"},{"alias_kind":"pith_short_16","alias_value":"7YMIYPI2VU65YY5N","created_at":"2026-07-05T05:11:22Z"},{"alias_kind":"pith_short_8","alias_value":"7YMIYPI2","created_at":"2026-07-05T05:11:22Z"}],"graph_snapshots":[{"event_id":"sha256:4fcaee5b3995c84bb9a2d9ac261dcf17e1b0bd2fa2d2309ac63a8c886970251a","target":"graph","created_at":"2026-07-05T05:11:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2205.14953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jakub Grudzien Kuba, Jun Wang, Muning Wen, Runji Lin, Weinan Zhang, Yaodong Yang, Ying Wen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2022-05-30T09:39:45Z","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14953","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9b1044e2082fb7e5bd2eb0e3699c299250a537918fdd51f07a39cea751787b64","target":"record","created_at":"2026-07-05T05:11:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b0f8fc7e48bb1749e4f99819c4a054de0db85d2c64b7bea785786d78d6b4c085","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2022-05-30T09:39:45Z","title_canon_sha256":"67c7a2ad79c85d528d9c1acedae1295271d0a0f3a5064ee1cea859110d56ea1f"},"schema_version":"1.0","source":{"id":"2205.14953","kind":"arxiv","version":3}},"canonical_sha256":"fe188c3d1aad3ddc63ada091efe6d265b502cd13a949f20ef685b7cb85f6b8ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe188c3d1aad3ddc63ada091efe6d265b502cd13a949f20ef685b7cb85f6b8ae","first_computed_at":"2026-07-05T05:11:22.267239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:22.267239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/nb31YFjzZL54uUH1NWyzoZNk3hYqIiHinGKAG+dx/G3sA9Opf6qaZLRgxXa+9BCJ/8N6FEoP8zDXLOmkNj9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:22.267739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14953","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b1044e2082fb7e5bd2eb0e3699c299250a537918fdd51f07a39cea751787b64","sha256:4fcaee5b3995c84bb9a2d9ac261dcf17e1b0bd2fa2d2309ac63a8c886970251a"],"state_sha256":"3d9f1bfd375dc1fb2eb718ffa0c482435ea2745524a5213dcde7b2c16086edd3"}