{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MS2TNFAL6OBRB3RHA3KJMXAUAF","short_pith_number":"pith:MS2TNFAL","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"},"canonical_sha256":"64b536940bf38310ee2706d4965c14017694c12b47fb138b32c9f45e2aff954e","source":{"kind":"arxiv","id":"2203.10603","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10603","created_at":"2026-07-05T09:53:58Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10603v1","created_at":"2026-07-05T09:53:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10603","created_at":"2026-07-05T09:53:58Z"},{"alias_kind":"pith_short_12","alias_value":"MS2TNFAL6OBR","created_at":"2026-07-05T09:53:58Z"},{"alias_kind":"pith_short_16","alias_value":"MS2TNFAL6OBRB3RH","created_at":"2026-07-05T09:53:58Z"},{"alias_kind":"pith_short_8","alias_value":"MS2TNFAL","created_at":"2026-07-05T09:53:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MS2TNFAL6OBRB3RHA3KJMXAUAF","target":"record","payload":{"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"},"canonical_sha256":"64b536940bf38310ee2706d4965c14017694c12b47fb138b32c9f45e2aff954e","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"},"source_kind":"arxiv","source_id":"2203.10603","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:53:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zK30vrFjwG8J1fHwtESOjLm/AyuUA4eGghdvys7Rr6GY1jSEHGv7NXeHkUEzI5qAuiAgVzMlpmNEYzWXp1h2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:28:32.176592Z"},"content_sha256":"039cbd2e223d8ee90efa72bc5ba463ce2314157b0f5a45938de2a891afcf70d3","schema_version":"1.0","event_id":"sha256:039cbd2e223d8ee90efa72bc5ba463ce2314157b0f5a45938de2a891afcf70d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MS2TNFAL6OBRB3RHA3KJMXAUAF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:53:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eMOQxR1saCf7kPDCCbe0rW2X0rlpT0tybYeA/3XeipqQKupxCqVrsFVfVEDeiR8/DJMatYiLfxH62jMmvc3KDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:28:32.176986Z"},"content_sha256":"d953fae02fa1a2e9b08f63ad8e43fc35c5adc13b1c1f8b413c7f19ec2b957c16","schema_version":"1.0","event_id":"sha256:d953fae02fa1a2e9b08f63ad8e43fc35c5adc13b1c1f8b413c7f19ec2b957c16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF/bundle.json","state_url":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T19:28:32Z","links":{"resolver":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF","bundle":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF/bundle.json","state":"https://pith.science/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MS2TNFAL6OBRB3RHA3KJMXAUAF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MS2TNFAL6OBRB3RHA3KJMXAUAF","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":"2881e4dec95d6a2d4d0e85ba535fa8f5ad5cbf7628c3df79770c54a9952437a1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-03-20T17:24:47Z","title_canon_sha256":"d5363bc399f161881a10f3b9ea424d565b586c01a386a870d9c8f761449af002"},"schema_version":"1.0","source":{"id":"2203.10603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10603","created_at":"2026-07-05T09:53:58Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10603v1","created_at":"2026-07-05T09:53:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10603","created_at":"2026-07-05T09:53:58Z"},{"alias_kind":"pith_short_12","alias_value":"MS2TNFAL6OBR","created_at":"2026-07-05T09:53:58Z"},{"alias_kind":"pith_short_16","alias_value":"MS2TNFAL6OBRB3RH","created_at":"2026-07-05T09:53:58Z"},{"alias_kind":"pith_short_8","alias_value":"MS2TNFAL","created_at":"2026-07-05T09:53:58Z"}],"graph_snapshots":[{"event_id":"sha256:d953fae02fa1a2e9b08f63ad8e43fc35c5adc13b1c1f8b413c7f19ec2b957c16","target":"graph","created_at":"2026-07-05T09:53:58Z","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/2203.10603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Weinan Zhang, Xihuai Wang, Zhicheng Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-03-20T17:24:47Z","title":"Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10603","kind":"arxiv","version":1},"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":"sha256:039cbd2e223d8ee90efa72bc5ba463ce2314157b0f5a45938de2a891afcf70d3","target":"record","created_at":"2026-07-05T09:53:58Z","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":"2881e4dec95d6a2d4d0e85ba535fa8f5ad5cbf7628c3df79770c54a9952437a1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-03-20T17:24:47Z","title_canon_sha256":"d5363bc399f161881a10f3b9ea424d565b586c01a386a870d9c8f761449af002"},"schema_version":"1.0","source":{"id":"2203.10603","kind":"arxiv","version":1}},"canonical_sha256":"64b536940bf38310ee2706d4965c14017694c12b47fb138b32c9f45e2aff954e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64b536940bf38310ee2706d4965c14017694c12b47fb138b32c9f45e2aff954e","first_computed_at":"2026-07-05T09:53:58.936953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:58.936953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h13NdP/VJFSd+tm7u3ddqh+E4bacpUre4cxV3ZQ0Kr+c/JScsXnC06TR8vBcGg7nShmw5UcTHn++DKPZDp4PAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:58.937434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.10603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:039cbd2e223d8ee90efa72bc5ba463ce2314157b0f5a45938de2a891afcf70d3","sha256:d953fae02fa1a2e9b08f63ad8e43fc35c5adc13b1c1f8b413c7f19ec2b957c16"],"state_sha256":"24019b80870f800fe8056c41d0a4efe77ad111a59f048c8b0f4bd58eff964a89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YLJyYUrXhnETudyHEshiyUPtyo6o/JFJsqsN1JhYa2/Ry0StvW4HbNdi2fNpU424spHe/mK17pz3iV0uFdidDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:28:32.179299Z","bundle_sha256":"d305603c34fb5586248e28f2ccc34dd58852b6e901f3e0c0ee318c05e5efe1b0"}}