{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SMCKYESUZ7NON2UYYE3O2LT7QZ","short_pith_number":"pith:SMCKYESU","schema_version":"1.0","canonical_sha256":"9304ac1254cfdae6ea98c136ed2e7f866335ceb5d4deea700cda112b8d825f90","source":{"kind":"arxiv","id":"2207.06559","version":2},"attestation_state":"computed","paper":{"title":"Scalable Model-based Policy Optimization for Decentralized Networked Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengdong Ma, Hao Dong, Jun Wang, Runji Lin, Yali Du, Yaodong Yang, Yuchen Liu","submitted_at":"2022-07-13T23:52:14Z","abstract_excerpt":"Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly requiring communications or shifting or resources. This work aims to improve data efficiency of multi-agent control by model-based learning. We consider networked systems where agents are cooperative and communicate only locally with their neighbors, and propose the decentralized model-based policy optimization framework (DMPO). In our method, each agent lear"},"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":"2207.06559","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T23:52:14Z","cross_cats_sorted":["cs.AI","cs.MA","math.OC","stat.ML"],"title_canon_sha256":"c76bd7d53461201efd4e8fb458a176016a3ca69e7735647183eab064687e089e","abstract_canon_sha256":"c21d1ce3b46184d6f24738c94745809e9dfaff6c6f23b2f8dce49ee95db1cd17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:53.906495Z","signature_b64":"Nz0WAKweSyQmXO5GfRyhhU7xs9qAwf/fRBxUYjgZYQ3v6r5wNuXtwBWGNnUbxiGClUwiOI15QE7YjkI2ijdrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9304ac1254cfdae6ea98c136ed2e7f866335ceb5d4deea700cda112b8d825f90","last_reissued_at":"2026-07-05T04:53:53.906143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:53.906143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Model-based Policy Optimization for Decentralized Networked Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengdong Ma, Hao Dong, Jun Wang, Runji Lin, Yali Du, Yaodong Yang, Yuchen Liu","submitted_at":"2022-07-13T23:52:14Z","abstract_excerpt":"Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly requiring communications or shifting or resources. This work aims to improve data efficiency of multi-agent control by model-based learning. We consider networked systems where agents are cooperative and communicate only locally with their neighbors, and propose the decentralized model-based policy optimization framework (DMPO). In our method, each agent lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06559","kind":"arxiv","version":2},"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/2207.06559/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":"2207.06559","created_at":"2026-07-05T04:53:53.906199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.06559v2","created_at":"2026-07-05T04:53:53.906199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06559","created_at":"2026-07-05T04:53:53.906199+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMCKYESUZ7NO","created_at":"2026-07-05T04:53:53.906199+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMCKYESUZ7NON2UY","created_at":"2026-07-05T04:53:53.906199+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMCKYESU","created_at":"2026-07-05T04:53:53.906199+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/SMCKYESUZ7NON2UYYE3O2LT7QZ","json":"https://pith.science/pith/SMCKYESUZ7NON2UYYE3O2LT7QZ.json","graph_json":"https://pith.science/api/pith-number/SMCKYESUZ7NON2UYYE3O2LT7QZ/graph.json","events_json":"https://pith.science/api/pith-number/SMCKYESUZ7NON2UYYE3O2LT7QZ/events.json","paper":"https://pith.science/paper/SMCKYESU"},"agent_actions":{"view_html":"https://pith.science/pith/SMCKYESUZ7NON2UYYE3O2LT7QZ","download_json":"https://pith.science/pith/SMCKYESUZ7NON2UYYE3O2LT7QZ.json","view_paper":"https://pith.science/paper/SMCKYESU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.06559&json=true","fetch_graph":"https://pith.science/api/pith-number/SMCKYESUZ7NON2UYYE3O2LT7QZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SMCKYESUZ7NON2UYYE3O2LT7QZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMCKYESUZ7NON2UYYE3O2LT7QZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMCKYESUZ7NON2UYYE3O2LT7QZ/action/storage_attestation","attest_author":"https://pith.science/pith/SMCKYESUZ7NON2UYYE3O2LT7QZ/action/author_attestation","sign_citation":"https://pith.science/pith/SMCKYESUZ7NON2UYYE3O2LT7QZ/action/citation_signature","submit_replication":"https://pith.science/pith/SMCKYESUZ7NON2UYYE3O2LT7QZ/action/replication_record"}},"created_at":"2026-07-05T04:53:53.906199+00:00","updated_at":"2026-07-05T04:53:53.906199+00:00"}