{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QI3Z2DFHWK6B4NGTQM46FUKZJN","short_pith_number":"pith:QI3Z2DFH","schema_version":"1.0","canonical_sha256":"82379d0ca7b2bc1e34d38339e2d1594b5d71ffd72260b1c281117591fb8904ec","source":{"kind":"arxiv","id":"1702.08584","version":1},"attestation_state":"computed","paper":{"title":"Model-based reinforcement learning in differential graphical games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.SY","authors_text":"Justin R. Klotz, Patrick Walters, Rushikesh Kamalapurkar, Warren E. Dixon","submitted_at":"2017-02-28T00:21:26Z","abstract_excerpt":"This paper seeks to combine differential game theory with the actor-critic-identifier architecture to determine forward-in-time, approximate optimal controllers for formation tracking in multi-agent systems, where the agents have uncertain heterogeneous nonlinear dynamics. A continuous control strategy is proposed, using communication feedback from extended neighbors on a communication topology that has a spanning tree. A model-based reinforcement learning technique is developed to cooperatively control a group of agents to track a trajectory in a desired formation. Simulation results are pres"},"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":"1702.08584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-02-28T00:21:26Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"e80ace691928eff0b7786f60bc64c0acf6cf41cc25444238a361366b6614e71b","abstract_canon_sha256":"131954ccad685bb12adbef061d666fb4c331d622ede024f5a12bb9697fa7d92e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:46.759537Z","signature_b64":"eKdHShMgUJKqistU0iIerZmpZ6ZbghtxwTOiOHLp7HzF7PBzho2yA/edR6AYhm9N15ni5bt6TsTvH0TJiRj3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82379d0ca7b2bc1e34d38339e2d1594b5d71ffd72260b1c281117591fb8904ec","last_reissued_at":"2026-05-18T00:39:46.758777Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:46.758777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-based reinforcement learning in differential graphical games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.SY","authors_text":"Justin R. Klotz, Patrick Walters, Rushikesh Kamalapurkar, Warren E. Dixon","submitted_at":"2017-02-28T00:21:26Z","abstract_excerpt":"This paper seeks to combine differential game theory with the actor-critic-identifier architecture to determine forward-in-time, approximate optimal controllers for formation tracking in multi-agent systems, where the agents have uncertain heterogeneous nonlinear dynamics. A continuous control strategy is proposed, using communication feedback from extended neighbors on a communication topology that has a spanning tree. A model-based reinforcement learning technique is developed to cooperatively control a group of agents to track a trajectory in a desired formation. Simulation results are pres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08584","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":""},"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":"1702.08584","created_at":"2026-05-18T00:39:46.758896+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08584v1","created_at":"2026-05-18T00:39:46.758896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08584","created_at":"2026-05-18T00:39:46.758896+00:00"},{"alias_kind":"pith_short_12","alias_value":"QI3Z2DFHWK6B","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QI3Z2DFHWK6B4NGT","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QI3Z2DFH","created_at":"2026-05-18T12:31:39.905425+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/QI3Z2DFHWK6B4NGTQM46FUKZJN","json":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN.json","graph_json":"https://pith.science/api/pith-number/QI3Z2DFHWK6B4NGTQM46FUKZJN/graph.json","events_json":"https://pith.science/api/pith-number/QI3Z2DFHWK6B4NGTQM46FUKZJN/events.json","paper":"https://pith.science/paper/QI3Z2DFH"},"agent_actions":{"view_html":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN","download_json":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN.json","view_paper":"https://pith.science/paper/QI3Z2DFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08584&json=true","fetch_graph":"https://pith.science/api/pith-number/QI3Z2DFHWK6B4NGTQM46FUKZJN/graph.json","fetch_events":"https://pith.science/api/pith-number/QI3Z2DFHWK6B4NGTQM46FUKZJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN/action/storage_attestation","attest_author":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN/action/author_attestation","sign_citation":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN/action/citation_signature","submit_replication":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN/action/replication_record"}},"created_at":"2026-05-18T00:39:46.758896+00:00","updated_at":"2026-05-18T00:39:46.758896+00:00"}