{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MS2TNFAL6OBRB3RHA3KJMXAUAF","short_pith_number":"pith:MS2TNFAL","schema_version":"1.0","canonical_sha256":"64b536940bf38310ee2706d4965c14017694c12b47fb138b32c9f45e2aff954e","source":{"kind":"arxiv","id":"2203.10603","version":1},"attestation_state":"computed","paper":{"title":"Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Weinan Zhang, Xihuai Wang, Zhicheng Zhang","submitted_at":"2022-03-20T17:24:47Z","abstract_excerpt":"Significant advances have recently been achieved in Multi-Agent Reinforcement Learning (MARL) which tackles sequential decision-making problems involving multiple participants. However, MARL requires a tremendous number of samples for effective training. On the other hand, model-based methods have been shown to achieve provable advantages of sample efficiency. However, the attempts of model-based methods to MARL have just started very recently. This paper presents a review of the existing research on model-based MARL, including theoretical analyses, algorithms, and applications, and analyzes t"},"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":"2203.10603","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-03-20T17:24:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d5363bc399f161881a10f3b9ea424d565b586c01a386a870d9c8f761449af002","abstract_canon_sha256":"2881e4dec95d6a2d4d0e85ba535fa8f5ad5cbf7628c3df79770c54a9952437a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:58.937434Z","signature_b64":"h13NdP/VJFSd+tm7u3ddqh+E4bacpUre4cxV3ZQ0Kr+c/JScsXnC06TR8vBcGg7nShmw5UcTHn++DKPZDp4PAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64b536940bf38310ee2706d4965c14017694c12b47fb138b32c9f45e2aff954e","last_reissued_at":"2026-07-05T09:53:58.936953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:58.936953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Weinan Zhang, Xihuai Wang, Zhicheng Zhang","submitted_at":"2022-03-20T17:24:47Z","abstract_excerpt":"Significant advances have recently been achieved in Multi-Agent Reinforcement Learning (MARL) which tackles sequential decision-making problems involving multiple participants. However, MARL requires a tremendous number of samples for effective training. On the other hand, model-based methods have been shown to achieve provable advantages of sample efficiency. However, the attempts of model-based methods to MARL have just started very recently. This paper presents a review of the existing research on model-based MARL, including theoretical analyses, algorithms, and applications, and analyzes t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10603","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/2203.10603/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":"2203.10603","created_at":"2026-07-05T09:53:58.937012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10603v1","created_at":"2026-07-05T09:53:58.937012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10603","created_at":"2026-07-05T09:53:58.937012+00:00"},{"alias_kind":"pith_short_12","alias_value":"MS2TNFAL6OBR","created_at":"2026-07-05T09:53:58.937012+00:00"},{"alias_kind":"pith_short_16","alias_value":"MS2TNFAL6OBRB3RH","created_at":"2026-07-05T09:53:58.937012+00:00"},{"alias_kind":"pith_short_8","alias_value":"MS2TNFAL","created_at":"2026-07-05T09:53:58.937012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08064","citing_title":"Cooperative Long Rope Skipping via Multi-Agent Reinforcement Learning","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF","json":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF.json","graph_json":"https://pith.science/api/pith-number/MS2TNFAL6OBRB3RHA3KJMXAUAF/graph.json","events_json":"https://pith.science/api/pith-number/MS2TNFAL6OBRB3RHA3KJMXAUAF/events.json","paper":"https://pith.science/paper/MS2TNFAL"},"agent_actions":{"view_html":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF","download_json":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF.json","view_paper":"https://pith.science/paper/MS2TNFAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10603&json=true","fetch_graph":"https://pith.science/api/pith-number/MS2TNFAL6OBRB3RHA3KJMXAUAF/graph.json","fetch_events":"https://pith.science/api/pith-number/MS2TNFAL6OBRB3RHA3KJMXAUAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF/action/storage_attestation","attest_author":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF/action/author_attestation","sign_citation":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF/action/citation_signature","submit_replication":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF/action/replication_record"}},"created_at":"2026-07-05T09:53:58.937012+00:00","updated_at":"2026-07-05T09:53:58.937012+00:00"}