{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:CBGFVY2UPKWL7OU5G56JUYU7H3","short_pith_number":"pith:CBGFVY2U","schema_version":"1.0","canonical_sha256":"104c5ae3547aacbfba9d377c9a629f3ef7e3356f84043ff625d7b2cd5c418b22","source":{"kind":"arxiv","id":"1506.00685","version":1},"attestation_state":"computed","paper":{"title":"Model-based reinforcement learning for infinite-horizon approximate optimal tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.SY","authors_text":"Lindsey Andrews, Patrick Walters, Rushikesh Kamalapurkar, Warren E. Dixon","submitted_at":"2015-06-01T21:43:01Z","abstract_excerpt":"This paper provides an approximate online adaptive solution to the infinite-horizon optimal tracking problem for control-affine continuous-time nonlinear systems with unknown drift dynamics. Model-based reinforcement learning is used to relax the persistence of excitation condition. Model-based reinforcement learning is implemented using a concurrent learning-based system identifier to simulate experience by evaluating the Bellman error over unexplored areas of the state space. Tracking of the desired trajectory and convergence of the developed policy to a neighborhood of the optimal policy ar"},"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":"1506.00685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-06-01T21:43:01Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"73b8b43e070adbd133066430015740333172b6f9342cd82f6d172eae43885066","abstract_canon_sha256":"cfc94fb762f5fbf9a94aa65cb886da9089d55e8a1f6422a577ba7c78df4771e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:48.216851Z","signature_b64":"rIpHKDCQT/VtG8OK/Mr9R9pyn7ELj7HclfTe/zho/TiQOE7JEK9CfybhF1kqTlKNWNJW1JPAuwlfFv5l3DL8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"104c5ae3547aacbfba9d377c9a629f3ef7e3356f84043ff625d7b2cd5c418b22","last_reissued_at":"2026-05-18T00:39:48.216174Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:48.216174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-based reinforcement learning for infinite-horizon approximate optimal tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.SY","authors_text":"Lindsey Andrews, Patrick Walters, Rushikesh Kamalapurkar, Warren E. Dixon","submitted_at":"2015-06-01T21:43:01Z","abstract_excerpt":"This paper provides an approximate online adaptive solution to the infinite-horizon optimal tracking problem for control-affine continuous-time nonlinear systems with unknown drift dynamics. Model-based reinforcement learning is used to relax the persistence of excitation condition. Model-based reinforcement learning is implemented using a concurrent learning-based system identifier to simulate experience by evaluating the Bellman error over unexplored areas of the state space. Tracking of the desired trajectory and convergence of the developed policy to a neighborhood of the optimal policy ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.00685","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":"1506.00685","created_at":"2026-05-18T00:39:48.216269+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.00685v1","created_at":"2026-05-18T00:39:48.216269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.00685","created_at":"2026-05-18T00:39:48.216269+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBGFVY2UPKWL","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBGFVY2UPKWL7OU5","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBGFVY2U","created_at":"2026-05-18T12:29:14.074870+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/CBGFVY2UPKWL7OU5G56JUYU7H3","json":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3.json","graph_json":"https://pith.science/api/pith-number/CBGFVY2UPKWL7OU5G56JUYU7H3/graph.json","events_json":"https://pith.science/api/pith-number/CBGFVY2UPKWL7OU5G56JUYU7H3/events.json","paper":"https://pith.science/paper/CBGFVY2U"},"agent_actions":{"view_html":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3","download_json":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3.json","view_paper":"https://pith.science/paper/CBGFVY2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.00685&json=true","fetch_graph":"https://pith.science/api/pith-number/CBGFVY2UPKWL7OU5G56JUYU7H3/graph.json","fetch_events":"https://pith.science/api/pith-number/CBGFVY2UPKWL7OU5G56JUYU7H3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3/action/storage_attestation","attest_author":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3/action/author_attestation","sign_citation":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3/action/citation_signature","submit_replication":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3/action/replication_record"}},"created_at":"2026-05-18T00:39:48.216269+00:00","updated_at":"2026-05-18T00:39:48.216269+00:00"}