{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5VOFBEJTEUIWEZ7LFWQPMS5SQG","short_pith_number":"pith:5VOFBEJT","schema_version":"1.0","canonical_sha256":"ed5c50913325116267eb2da0f64bb281b3f7f1a085410c39daa6cbd0180527c2","source":{"kind":"arxiv","id":"1711.11422","version":2},"attestation_state":"computed","paper":{"title":"Data-Based Optimal Control of Multi-Agent Systems: A Reinforcement Learning Design Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hongwei Zhang, Jilie Zhang, Zhanshan Wang","submitted_at":"2017-11-30T14:31:04Z","abstract_excerpt":"This paper studies optimal consensus tracking problem of heterogeneous linear multi-agent systems. By introducing tracking error dynamics, the optimal tracking problem is reformulated as finding a Nash-equilibrium solution of a multi-player games, which can be done by solving associated coupled Hamilton-Jacobi (HJ) equations. A data-based error estimator is designed to obtain the data-based control for the multi-agent systems. Using the quadratic functional to approximate the every agent's value function, we can obtain the optimal cooperative control by input-output (I/O) $Q$-learning algorith"},"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":"1711.11422","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-11-30T14:31:04Z","cross_cats_sorted":[],"title_canon_sha256":"59c2445d9eca7c243ec7ae9b55fe8dced1363acbd1cc3d69355f134972524718","abstract_canon_sha256":"3de613052cc678aace24e14ab40a69a31be1f58f7e3945ac75b230011f3d256f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:53.329619Z","signature_b64":"gpHrkKF2ZkttkglSeXdpUHsJa0o95B+3erFkXC2M+WvVPBdvbgMUCnqBxUx6V1xoCPEQqGOPqjSc18dzv+qDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed5c50913325116267eb2da0f64bb281b3f7f1a085410c39daa6cbd0180527c2","last_reissued_at":"2026-05-17T23:45:53.329031Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:53.329031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Based Optimal Control of Multi-Agent Systems: A Reinforcement Learning Design Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hongwei Zhang, Jilie Zhang, Zhanshan Wang","submitted_at":"2017-11-30T14:31:04Z","abstract_excerpt":"This paper studies optimal consensus tracking problem of heterogeneous linear multi-agent systems. By introducing tracking error dynamics, the optimal tracking problem is reformulated as finding a Nash-equilibrium solution of a multi-player games, which can be done by solving associated coupled Hamilton-Jacobi (HJ) equations. A data-based error estimator is designed to obtain the data-based control for the multi-agent systems. Using the quadratic functional to approximate the every agent's value function, we can obtain the optimal cooperative control by input-output (I/O) $Q$-learning algorith"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11422","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":""},"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":"1711.11422","created_at":"2026-05-17T23:45:53.329143+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.11422v2","created_at":"2026-05-17T23:45:53.329143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11422","created_at":"2026-05-17T23:45:53.329143+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VOFBEJTEUIW","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VOFBEJTEUIWEZ7L","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VOFBEJT","created_at":"2026-05-18T12:31:00.734936+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/5VOFBEJTEUIWEZ7LFWQPMS5SQG","json":"https://pith.science/pith/5VOFBEJTEUIWEZ7LFWQPMS5SQG.json","graph_json":"https://pith.science/api/pith-number/5VOFBEJTEUIWEZ7LFWQPMS5SQG/graph.json","events_json":"https://pith.science/api/pith-number/5VOFBEJTEUIWEZ7LFWQPMS5SQG/events.json","paper":"https://pith.science/paper/5VOFBEJT"},"agent_actions":{"view_html":"https://pith.science/pith/5VOFBEJTEUIWEZ7LFWQPMS5SQG","download_json":"https://pith.science/pith/5VOFBEJTEUIWEZ7LFWQPMS5SQG.json","view_paper":"https://pith.science/paper/5VOFBEJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.11422&json=true","fetch_graph":"https://pith.science/api/pith-number/5VOFBEJTEUIWEZ7LFWQPMS5SQG/graph.json","fetch_events":"https://pith.science/api/pith-number/5VOFBEJTEUIWEZ7LFWQPMS5SQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VOFBEJTEUIWEZ7LFWQPMS5SQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VOFBEJTEUIWEZ7LFWQPMS5SQG/action/storage_attestation","attest_author":"https://pith.science/pith/5VOFBEJTEUIWEZ7LFWQPMS5SQG/action/author_attestation","sign_citation":"https://pith.science/pith/5VOFBEJTEUIWEZ7LFWQPMS5SQG/action/citation_signature","submit_replication":"https://pith.science/pith/5VOFBEJTEUIWEZ7LFWQPMS5SQG/action/replication_record"}},"created_at":"2026-05-17T23:45:53.329143+00:00","updated_at":"2026-05-17T23:45:53.329143+00:00"}