{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OQLZHVZCJMLNPGZO334ZMOZUBS","short_pith_number":"pith:OQLZHVZC","schema_version":"1.0","canonical_sha256":"741793d7224b16d79b2edef9963b340c8841f196bbd39706aa77e077e6574105","source":{"kind":"arxiv","id":"2308.11743","version":1},"attestation_state":"computed","paper":{"title":"Model-free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Aritra Mitra, Han Wang, James Anderson, Leonardo F. Toso","submitted_at":"2023-08-22T19:09:29Z","abstract_excerpt":"We study a model-free federated linear quadratic regulator (LQR) problem where M agents with unknown, distinct yet similar dynamics collaboratively learn an optimal policy to minimize an average quadratic cost while keeping their data private. To exploit the similarity of the agents' dynamics, we propose to use federated learning (FL) to allow the agents to periodically communicate with a central server to train policies by leveraging a larger dataset from all the agents. With this setup, we seek to understand the following questions: (i) Is the learned common policy stabilizing for all agents"},"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":"2308.11743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-08-22T19:09:29Z","cross_cats_sorted":[],"title_canon_sha256":"54bf9aecdc26fa1edc7cf356d7946a187ca31d4bc88dcf957f1adaf4bd8643cd","abstract_canon_sha256":"6cf0ac2264e19a442fe6b107548b223e64d0572e5c2d592fc7d5a5db822bfd5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:54.319568Z","signature_b64":"Iuh4kjkPyb0VD93tVf16I/a4Rmq5RevJyT6LrOX4Uup+TH+Je9lQEcZQyfU0NrLG75Zyj/ss2evvlasAU5zPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"741793d7224b16d79b2edef9963b340c8841f196bbd39706aa77e077e6574105","last_reissued_at":"2026-07-05T06:43:54.319042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:54.319042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Aritra Mitra, Han Wang, James Anderson, Leonardo F. Toso","submitted_at":"2023-08-22T19:09:29Z","abstract_excerpt":"We study a model-free federated linear quadratic regulator (LQR) problem where M agents with unknown, distinct yet similar dynamics collaboratively learn an optimal policy to minimize an average quadratic cost while keeping their data private. To exploit the similarity of the agents' dynamics, we propose to use federated learning (FL) to allow the agents to periodically communicate with a central server to train policies by leveraging a larger dataset from all the agents. With this setup, we seek to understand the following questions: (i) Is the learned common policy stabilizing for all agents"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11743","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/2308.11743/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":"2308.11743","created_at":"2026-07-05T06:43:54.319104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.11743v1","created_at":"2026-07-05T06:43:54.319104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11743","created_at":"2026-07-05T06:43:54.319104+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQLZHVZCJMLN","created_at":"2026-07-05T06:43:54.319104+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQLZHVZCJMLNPGZO","created_at":"2026-07-05T06:43:54.319104+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQLZHVZC","created_at":"2026-07-05T06:43:54.319104+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05088","citing_title":"Scalar Federated Learning for Linear Quadratic Regulator","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16730","citing_title":"Multitask LQG Control: Performance and Generalization Bounds","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQLZHVZCJMLNPGZO334ZMOZUBS","json":"https://pith.science/pith/OQLZHVZCJMLNPGZO334ZMOZUBS.json","graph_json":"https://pith.science/api/pith-number/OQLZHVZCJMLNPGZO334ZMOZUBS/graph.json","events_json":"https://pith.science/api/pith-number/OQLZHVZCJMLNPGZO334ZMOZUBS/events.json","paper":"https://pith.science/paper/OQLZHVZC"},"agent_actions":{"view_html":"https://pith.science/pith/OQLZHVZCJMLNPGZO334ZMOZUBS","download_json":"https://pith.science/pith/OQLZHVZCJMLNPGZO334ZMOZUBS.json","view_paper":"https://pith.science/paper/OQLZHVZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.11743&json=true","fetch_graph":"https://pith.science/api/pith-number/OQLZHVZCJMLNPGZO334ZMOZUBS/graph.json","fetch_events":"https://pith.science/api/pith-number/OQLZHVZCJMLNPGZO334ZMOZUBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQLZHVZCJMLNPGZO334ZMOZUBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQLZHVZCJMLNPGZO334ZMOZUBS/action/storage_attestation","attest_author":"https://pith.science/pith/OQLZHVZCJMLNPGZO334ZMOZUBS/action/author_attestation","sign_citation":"https://pith.science/pith/OQLZHVZCJMLNPGZO334ZMOZUBS/action/citation_signature","submit_replication":"https://pith.science/pith/OQLZHVZCJMLNPGZO334ZMOZUBS/action/replication_record"}},"created_at":"2026-07-05T06:43:54.319104+00:00","updated_at":"2026-07-05T06:43:54.319104+00:00"}