{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GE57OBIPTESOK43L6RVGYSFHP4","short_pith_number":"pith:GE57OBIP","schema_version":"1.0","canonical_sha256":"313bf7050f9924e5736bf46a6c48a77f10b4af4898491252a1399d3035f443e6","source":{"kind":"arxiv","id":"2506.18537","version":1},"attestation_state":"computed","paper":{"title":"Transformer World Model for Sample Efficient Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Azad Deihim, Dimitra Apostolopoulou, Eduardo Alonso","submitted_at":"2025-06-23T11:47:17Z","abstract_excerpt":"We present the Multi-Agent Transformer World Model (MATWM), a novel transformer-based world model designed for multi-agent reinforcement learning in both vector- and image-based environments. MATWM combines a decentralized imagination framework with a semi-centralized critic and a teammate prediction module, enabling agents to model and anticipate the behavior of others under partial observability. To address non-stationarity, we incorporate a prioritized replay mechanism that trains the world model on recent experiences, allowing it to adapt to agents' evolving policies. We evaluated MATWM on"},"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":"2506.18537","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T11:47:17Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"e695637a68d7de83547d433ddd3a75952de47d1a8f68c341b9df2c9142e4b476","abstract_canon_sha256":"6284de8412b05b8a7d76be621eb25f97941ef59a7af89a40809d145a52d4b272"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:51.673380Z","signature_b64":"SUn1nboQNa7JNZoQig+MntfnhgDidIo067uDaYfnYDKY0lUcydkE5c5g0pqpnGHHLsPVkkkcZyEk0x0UP4ghCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"313bf7050f9924e5736bf46a6c48a77f10b4af4898491252a1399d3035f443e6","last_reissued_at":"2026-07-05T11:25:51.672956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:51.672956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer World Model for Sample Efficient Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Azad Deihim, Dimitra Apostolopoulou, Eduardo Alonso","submitted_at":"2025-06-23T11:47:17Z","abstract_excerpt":"We present the Multi-Agent Transformer World Model (MATWM), a novel transformer-based world model designed for multi-agent reinforcement learning in both vector- and image-based environments. MATWM combines a decentralized imagination framework with a semi-centralized critic and a teammate prediction module, enabling agents to model and anticipate the behavior of others under partial observability. To address non-stationarity, we incorporate a prioritized replay mechanism that trains the world model on recent experiences, allowing it to adapt to agents' evolving policies. We evaluated MATWM on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18537","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/2506.18537/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":"2506.18537","created_at":"2026-07-05T11:25:51.673012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18537v1","created_at":"2026-07-05T11:25:51.673012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18537","created_at":"2026-07-05T11:25:51.673012+00:00"},{"alias_kind":"pith_short_12","alias_value":"GE57OBIPTESO","created_at":"2026-07-05T11:25:51.673012+00:00"},{"alias_kind":"pith_short_16","alias_value":"GE57OBIPTESOK43L","created_at":"2026-07-05T11:25:51.673012+00:00"},{"alias_kind":"pith_short_8","alias_value":"GE57OBIP","created_at":"2026-07-05T11:25:51.673012+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/GE57OBIPTESOK43L6RVGYSFHP4","json":"https://pith.science/pith/GE57OBIPTESOK43L6RVGYSFHP4.json","graph_json":"https://pith.science/api/pith-number/GE57OBIPTESOK43L6RVGYSFHP4/graph.json","events_json":"https://pith.science/api/pith-number/GE57OBIPTESOK43L6RVGYSFHP4/events.json","paper":"https://pith.science/paper/GE57OBIP"},"agent_actions":{"view_html":"https://pith.science/pith/GE57OBIPTESOK43L6RVGYSFHP4","download_json":"https://pith.science/pith/GE57OBIPTESOK43L6RVGYSFHP4.json","view_paper":"https://pith.science/paper/GE57OBIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18537&json=true","fetch_graph":"https://pith.science/api/pith-number/GE57OBIPTESOK43L6RVGYSFHP4/graph.json","fetch_events":"https://pith.science/api/pith-number/GE57OBIPTESOK43L6RVGYSFHP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GE57OBIPTESOK43L6RVGYSFHP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GE57OBIPTESOK43L6RVGYSFHP4/action/storage_attestation","attest_author":"https://pith.science/pith/GE57OBIPTESOK43L6RVGYSFHP4/action/author_attestation","sign_citation":"https://pith.science/pith/GE57OBIPTESOK43L6RVGYSFHP4/action/citation_signature","submit_replication":"https://pith.science/pith/GE57OBIPTESOK43L6RVGYSFHP4/action/replication_record"}},"created_at":"2026-07-05T11:25:51.673012+00:00","updated_at":"2026-07-05T11:25:51.673012+00:00"}