{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SMCKYESUZ7NON2UYYE3O2LT7QZ","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":"c21d1ce3b46184d6f24738c94745809e9dfaff6c6f23b2f8dce49ee95db1cd17","cross_cats_sorted":["cs.AI","cs.MA","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T23:52:14Z","title_canon_sha256":"c76bd7d53461201efd4e8fb458a176016a3ca69e7735647183eab064687e089e"},"schema_version":"1.0","source":{"id":"2207.06559","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06559","created_at":"2026-07-05T04:53:53Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06559v2","created_at":"2026-07-05T04:53:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06559","created_at":"2026-07-05T04:53:53Z"},{"alias_kind":"pith_short_12","alias_value":"SMCKYESUZ7NO","created_at":"2026-07-05T04:53:53Z"},{"alias_kind":"pith_short_16","alias_value":"SMCKYESUZ7NON2UY","created_at":"2026-07-05T04:53:53Z"},{"alias_kind":"pith_short_8","alias_value":"SMCKYESU","created_at":"2026-07-05T04:53:53Z"}],"graph_snapshots":[{"event_id":"sha256:69ab100c62ab3f0150a9f16ffe0fabf06e344dd640428ad8b963e3b355bcf3a4","target":"graph","created_at":"2026-07-05T04:53:53Z","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/2207.06559/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chengdong Ma, Hao Dong, Jun Wang, Runji Lin, Yali Du, Yaodong Yang, Yuchen Liu","cross_cats":["cs.AI","cs.MA","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T23:52:14Z","title":"Scalable Model-based Policy Optimization for Decentralized Networked Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06559","kind":"arxiv","version":2},"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":"sha256:2bc6e7d9ca981a001a17710da114f2b8c466c5c0af80d4650bd4bf9c7e854357","target":"record","created_at":"2026-07-05T04:53:53Z","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":"c21d1ce3b46184d6f24738c94745809e9dfaff6c6f23b2f8dce49ee95db1cd17","cross_cats_sorted":["cs.AI","cs.MA","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T23:52:14Z","title_canon_sha256":"c76bd7d53461201efd4e8fb458a176016a3ca69e7735647183eab064687e089e"},"schema_version":"1.0","source":{"id":"2207.06559","kind":"arxiv","version":2}},"canonical_sha256":"9304ac1254cfdae6ea98c136ed2e7f866335ceb5d4deea700cda112b8d825f90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9304ac1254cfdae6ea98c136ed2e7f866335ceb5d4deea700cda112b8d825f90","first_computed_at":"2026-07-05T04:53:53.906143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:53:53.906143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nz0WAKweSyQmXO5GfRyhhU7xs9qAwf/fRBxUYjgZYQ3v6r5wNuXtwBWGNnUbxiGClUwiOI15QE7YjkI2ijdrDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:53:53.906495Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.06559","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bc6e7d9ca981a001a17710da114f2b8c466c5c0af80d4650bd4bf9c7e854357","sha256:69ab100c62ab3f0150a9f16ffe0fabf06e344dd640428ad8b963e3b355bcf3a4"],"state_sha256":"93fed9a9eaa1ad212ed68dbc69614c7f79b1299b92755bc2077a8407eb19143a"}