{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TVINA4R6GNNSPMZVGYJWITZ6BN","short_pith_number":"pith:TVINA4R6","schema_version":"1.0","canonical_sha256":"9d50d0723e335b27b3353613644f3e0b5d16eeee5313b0ddf0ca6c8980907c2f","source":{"kind":"arxiv","id":"2303.17984","version":1},"attestation_state":"computed","paper":{"title":"Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Chao Yu, Chen Chen, Hankz Hankui Zhuo, Jianye Hao, Zifan Wu","submitted_at":"2023-03-31T11:42:04Z","abstract_excerpt":"Research in model-based reinforcement learning has made significant progress in recent years. Compared to single-agent settings, the exponential dimension growth of the joint state-action space in multi-agent systems dramatically increases the complexity of the environment dynamics, which makes it infeasible to learn an accurate global model and thus necessitates the use of agent-wise local models. However, during multi-step model rollouts, the prediction of one local model can affect the predictions of other local models in the next step. As a result, local prediction errors can be propagated"},"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":"2303.17984","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2023-03-31T11:42:04Z","cross_cats_sorted":[],"title_canon_sha256":"d4a6b4c94a7b95b120e66ef96fca98bc3a409a700aa5c92b707bce992f3c9970","abstract_canon_sha256":"8455688a33dbcbb4a3925e81e4a28f27bdba311967ff5ad25c5fc3311eb9cd25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:48.570143Z","signature_b64":"orI7WEkud6SFB2NVKN+i6zXldklggH7huZoR70vcVIlSgvN8Zwqq02e5O6Sj+o2gCfQt6ksXSsXgY4itlrbdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d50d0723e335b27b3353613644f3e0b5d16eeee5313b0ddf0ca6c8980907c2f","last_reissued_at":"2026-07-05T05:56:48.569655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:48.569655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Chao Yu, Chen Chen, Hankz Hankui Zhuo, Jianye Hao, Zifan Wu","submitted_at":"2023-03-31T11:42:04Z","abstract_excerpt":"Research in model-based reinforcement learning has made significant progress in recent years. Compared to single-agent settings, the exponential dimension growth of the joint state-action space in multi-agent systems dramatically increases the complexity of the environment dynamics, which makes it infeasible to learn an accurate global model and thus necessitates the use of agent-wise local models. However, during multi-step model rollouts, the prediction of one local model can affect the predictions of other local models in the next step. As a result, local prediction errors can be propagated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17984","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/2303.17984/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":"2303.17984","created_at":"2026-07-05T05:56:48.569712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17984v1","created_at":"2026-07-05T05:56:48.569712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17984","created_at":"2026-07-05T05:56:48.569712+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVINA4R6GNNS","created_at":"2026-07-05T05:56:48.569712+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVINA4R6GNNSPMZV","created_at":"2026-07-05T05:56:48.569712+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVINA4R6","created_at":"2026-07-05T05:56:48.569712+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/TVINA4R6GNNSPMZVGYJWITZ6BN","json":"https://pith.science/pith/TVINA4R6GNNSPMZVGYJWITZ6BN.json","graph_json":"https://pith.science/api/pith-number/TVINA4R6GNNSPMZVGYJWITZ6BN/graph.json","events_json":"https://pith.science/api/pith-number/TVINA4R6GNNSPMZVGYJWITZ6BN/events.json","paper":"https://pith.science/paper/TVINA4R6"},"agent_actions":{"view_html":"https://pith.science/pith/TVINA4R6GNNSPMZVGYJWITZ6BN","download_json":"https://pith.science/pith/TVINA4R6GNNSPMZVGYJWITZ6BN.json","view_paper":"https://pith.science/paper/TVINA4R6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17984&json=true","fetch_graph":"https://pith.science/api/pith-number/TVINA4R6GNNSPMZVGYJWITZ6BN/graph.json","fetch_events":"https://pith.science/api/pith-number/TVINA4R6GNNSPMZVGYJWITZ6BN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVINA4R6GNNSPMZVGYJWITZ6BN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVINA4R6GNNSPMZVGYJWITZ6BN/action/storage_attestation","attest_author":"https://pith.science/pith/TVINA4R6GNNSPMZVGYJWITZ6BN/action/author_attestation","sign_citation":"https://pith.science/pith/TVINA4R6GNNSPMZVGYJWITZ6BN/action/citation_signature","submit_replication":"https://pith.science/pith/TVINA4R6GNNSPMZVGYJWITZ6BN/action/replication_record"}},"created_at":"2026-07-05T05:56:48.569712+00:00","updated_at":"2026-07-05T05:56:48.569712+00:00"}