{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:FU2U6JQM7GS5LZBMZK7CWSUBDZ","short_pith_number":"pith:FU2U6JQM","canonical_record":{"source":{"id":"1410.2954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-10-11T06:06:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5d1433bb80c6b9c9faf7b6647b2e72b2597b12162d1c71dc23b9540b895778a2","abstract_canon_sha256":"2db34d9434daa8e24509f43b5786c1f8bef335661e115fa3a225582d65e6a30a"},"schema_version":"1.0"},"canonical_sha256":"2d354f260cf9a5d5e42ccabe2b4a811e5441fa2f7578f110ae71c30a315b296c","source":{"kind":"arxiv","id":"1410.2954","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.2954","created_at":"2026-05-18T02:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"1410.2954v1","created_at":"2026-05-18T02:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.2954","created_at":"2026-05-18T02:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"FU2U6JQM7GS5","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FU2U6JQM7GS5LZBM","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FU2U6JQM","created_at":"2026-05-18T12:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:FU2U6JQM7GS5LZBMZK7CWSUBDZ","target":"record","payload":{"canonical_record":{"source":{"id":"1410.2954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-10-11T06:06:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5d1433bb80c6b9c9faf7b6647b2e72b2597b12162d1c71dc23b9540b895778a2","abstract_canon_sha256":"2db34d9434daa8e24509f43b5786c1f8bef335661e115fa3a225582d65e6a30a"},"schema_version":"1.0"},"canonical_sha256":"2d354f260cf9a5d5e42ccabe2b4a811e5441fa2f7578f110ae71c30a315b296c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:40:17.395805Z","signature_b64":"NzZvaFguF9u945hcNqVgJDjW1auLDPZTw0zngDC4GWXRGSPIByUkxPkxckSGOiOrresCZTlAwgaE3e1GSgDeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d354f260cf9a5d5e42ccabe2b4a811e5441fa2f7578f110ae71c30a315b296c","last_reissued_at":"2026-05-18T02:40:17.395366Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:40:17.395366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1410.2954","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:40:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P6Msx3ZZXN+wHSGOkbw/ZfxzAP8lCROr0zoeFhoclbXTcnTUoy69oEEyKlYs4tlbsTVvocaAnN4LHHE9DBDiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T06:04:33.925821Z"},"content_sha256":"6260b570449c224f49afe6ebd7b9572009d74aa63725e8b08c5fad9943e9c8b3","schema_version":"1.0","event_id":"sha256:6260b570449c224f49afe6ebd7b9572009d74aa63725e8b08c5fad9943e9c8b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:FU2U6JQM7GS5LZBMZK7CWSUBDZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Q-learning for Optimal Control of Continuous-time Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.SY","authors_text":"Biao Luo, Derong Liu, Tingwen Huang","submitted_at":"2014-10-11T06:06:20Z","abstract_excerpt":"In this paper, two Q-learning (QL) methods are proposed and their convergence theories are established for addressing the model-free optimal control problem of general nonlinear continuous-time systems. By introducing the Q-function for continuous-time systems, policy iteration based QL (PIQL) and value iteration based QL (VIQL) algorithms are proposed for learning the optimal control policy from real system data rather than using mathematical system model. It is proved that both PIQL and VIQL methods generate a nonincreasing Q-function sequence, which converges to the optimal Q-function. For "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.2954","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:40:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PKkpZFsBhdAAPndelrBnLD/HUPB2idlhnm3LvyT5ruZACDafC/DWSDoNdSrK5bYAxK9ZaurWSMpS4+YRWybiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T06:04:33.926546Z"},"content_sha256":"eecb175783506285a0fa8cecaf19a10da4daf0e3059d7f1444d4ac6a6a6efcca","schema_version":"1.0","event_id":"sha256:eecb175783506285a0fa8cecaf19a10da4daf0e3059d7f1444d4ac6a6a6efcca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FU2U6JQM7GS5LZBMZK7CWSUBDZ/bundle.json","state_url":"https://pith.science/pith/FU2U6JQM7GS5LZBMZK7CWSUBDZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FU2U6JQM7GS5LZBMZK7CWSUBDZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-09T06:04:33Z","links":{"resolver":"https://pith.science/pith/FU2U6JQM7GS5LZBMZK7CWSUBDZ","bundle":"https://pith.science/pith/FU2U6JQM7GS5LZBMZK7CWSUBDZ/bundle.json","state":"https://pith.science/pith/FU2U6JQM7GS5LZBMZK7CWSUBDZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FU2U6JQM7GS5LZBMZK7CWSUBDZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:FU2U6JQM7GS5LZBMZK7CWSUBDZ","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":"2db34d9434daa8e24509f43b5786c1f8bef335661e115fa3a225582d65e6a30a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-10-11T06:06:20Z","title_canon_sha256":"5d1433bb80c6b9c9faf7b6647b2e72b2597b12162d1c71dc23b9540b895778a2"},"schema_version":"1.0","source":{"id":"1410.2954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.2954","created_at":"2026-05-18T02:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"1410.2954v1","created_at":"2026-05-18T02:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.2954","created_at":"2026-05-18T02:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"FU2U6JQM7GS5","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FU2U6JQM7GS5LZBM","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FU2U6JQM","created_at":"2026-05-18T12:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:eecb175783506285a0fa8cecaf19a10da4daf0e3059d7f1444d4ac6a6a6efcca","target":"graph","created_at":"2026-05-18T02:40:17Z","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"},"paper":{"abstract_excerpt":"In this paper, two Q-learning (QL) methods are proposed and their convergence theories are established for addressing the model-free optimal control problem of general nonlinear continuous-time systems. By introducing the Q-function for continuous-time systems, policy iteration based QL (PIQL) and value iteration based QL (VIQL) algorithms are proposed for learning the optimal control policy from real system data rather than using mathematical system model. It is proved that both PIQL and VIQL methods generate a nonincreasing Q-function sequence, which converges to the optimal Q-function. For ","authors_text":"Biao Luo, Derong Liu, Tingwen Huang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-10-11T06:06:20Z","title":"Q-learning for Optimal Control of Continuous-time Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.2954","kind":"arxiv","version":1},"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":"sha256:6260b570449c224f49afe6ebd7b9572009d74aa63725e8b08c5fad9943e9c8b3","target":"record","created_at":"2026-05-18T02:40:17Z","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":"2db34d9434daa8e24509f43b5786c1f8bef335661e115fa3a225582d65e6a30a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-10-11T06:06:20Z","title_canon_sha256":"5d1433bb80c6b9c9faf7b6647b2e72b2597b12162d1c71dc23b9540b895778a2"},"schema_version":"1.0","source":{"id":"1410.2954","kind":"arxiv","version":1}},"canonical_sha256":"2d354f260cf9a5d5e42ccabe2b4a811e5441fa2f7578f110ae71c30a315b296c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d354f260cf9a5d5e42ccabe2b4a811e5441fa2f7578f110ae71c30a315b296c","first_computed_at":"2026-05-18T02:40:17.395366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:40:17.395366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NzZvaFguF9u945hcNqVgJDjW1auLDPZTw0zngDC4GWXRGSPIByUkxPkxckSGOiOrresCZTlAwgaE3e1GSgDeBA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:40:17.395805Z","signed_message":"canonical_sha256_bytes"},"source_id":"1410.2954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6260b570449c224f49afe6ebd7b9572009d74aa63725e8b08c5fad9943e9c8b3","sha256:eecb175783506285a0fa8cecaf19a10da4daf0e3059d7f1444d4ac6a6a6efcca"],"state_sha256":"652004ee0a024c5ff468418ccd8c9d838f4b474e9239052747e88e8d013e7aa2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Fl/vyQ1USw+uKQcajTJxwRH8IILfomr2SnrID6gxN4xMEIV0tEMan0JjTXTtRCQx5E3+D2CNwE5X/H/x7GbDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T06:04:33.930449Z","bundle_sha256":"11ee357c09565489d43362c345b109e77ba29486574eb3c3704b7e2d362c52cc"}}