{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JFZ5EUYNILNMFYYZJMYSUXU3W3","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":"d30b91b450752dd64c01ec5ed66af1c04331699fc6ffb6db31f0fa1949416686","cross_cats_sorted":["cs.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2021-04-19T21:46:11Z","title_canon_sha256":"e2d5dcf4ceef241f54a6b22930f2ca88afcd1418f4178cf450918c7fb57f5a2c"},"schema_version":"1.0","source":{"id":"2104.09652","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09652","created_at":"2026-07-05T02:36:23Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09652v2","created_at":"2026-07-05T02:36:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09652","created_at":"2026-07-05T02:36:23Z"},{"alias_kind":"pith_short_12","alias_value":"JFZ5EUYNILNM","created_at":"2026-07-05T02:36:23Z"},{"alias_kind":"pith_short_16","alias_value":"JFZ5EUYNILNMFYYZ","created_at":"2026-07-05T02:36:23Z"},{"alias_kind":"pith_short_8","alias_value":"JFZ5EUYN","created_at":"2026-07-05T02:36:23Z"}],"graph_snapshots":[{"event_id":"sha256:5bfaedec1e05688e6fa0ec709043b5a05e395fe43ee982516679615668b9e3fd","target":"graph","created_at":"2026-07-05T02:36:23Z","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/2104.09652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work presents a technique for learning systems, where the learning process is guided by knowledge of the physics of the system. In particular, we solve the problem of the two-point boundary optimal control problem of linear time-varying systems with unknown model dynamics using reinforcement learning. Borrowing techniques from singular perturbation theory, we transform the time-varying optimal control problem into a couple of time-invariant subproblems. This allows the utilization of an off-policy iteration method to learn the controller gains. We show that the performance of the learning","authors_text":"Almuatazbellah Boker, Hoda Eldardiry, Vasanth Reddy","cross_cats":["cs.SY","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2021-04-19T21:46:11Z","title":"Singular Perturbation-based Reinforcement Learning of Two-Point Boundary Optimal Control Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09652","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":"sha256:789cf2dd34fe8e97dc22f77651592c9a0dcf01de3c581cb5358051ee6b2834bb","target":"record","created_at":"2026-07-05T02:36:23Z","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":"d30b91b450752dd64c01ec5ed66af1c04331699fc6ffb6db31f0fa1949416686","cross_cats_sorted":["cs.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2021-04-19T21:46:11Z","title_canon_sha256":"e2d5dcf4ceef241f54a6b22930f2ca88afcd1418f4178cf450918c7fb57f5a2c"},"schema_version":"1.0","source":{"id":"2104.09652","kind":"arxiv","version":2}},"canonical_sha256":"4973d2530d42dac2e3194b312a5e9bb6ebe3bbb4a9643dde915653e246fdeb29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4973d2530d42dac2e3194b312a5e9bb6ebe3bbb4a9643dde915653e246fdeb29","first_computed_at":"2026-07-05T02:36:23.676156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:36:23.676156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2pRcYhKzDPNKgQ2rjVJlaf+i6qFDjHmjZqcNkm/kY3afuVvTQ1LJf78dMETO6C1EKK2Iva8Y87d7aqBgaF9iDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:36:23.676577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.09652","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:789cf2dd34fe8e97dc22f77651592c9a0dcf01de3c581cb5358051ee6b2834bb","sha256:5bfaedec1e05688e6fa0ec709043b5a05e395fe43ee982516679615668b9e3fd"],"state_sha256":"384b90cb26ee3b1ecd2fd41476be9daca3019d2e2b75922e64738bda8c70fdb5"}