{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4FONINDVYTKO7G4MJ2Y47V7ERJ","short_pith_number":"pith:4FONINDV","schema_version":"1.0","canonical_sha256":"e15cd43475c4d4ef9b8c4eb1cfd7e48a6f075303dfb7d3dba0362e4aefc4dc42","source":{"kind":"arxiv","id":"2305.01461","version":3},"attestation_state":"computed","paper":{"title":"Mixed-Integer Optimal Control via Reinforcement Learning: A Case Study on Hybrid Electric Vehicle Energy Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY"],"primary_cat":"eess.SY","authors_text":"Jinming Xu, Nasser Lashgarian Azad, Yuan Lin","submitted_at":"2023-05-02T14:42:21Z","abstract_excerpt":"Many optimal control problems require the simultaneous output of discrete and continuous control variables. These problems are usually formulated as mixed-integer optimal control (MIOC) problems, which are challenging to solve due to the complexity of the solution space. Numerical methods such as branch-and-bound are computationally expensive and undesirable for real-time control. This paper proposes a novel hybrid-action reinforcement learning (HARL) algorithm, twin delayed deep deterministic actor-Q (TD3AQ), for MIOC problems. TD3AQ combines the advantages of both actor-critic and Q-learning"},"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":"2305.01461","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-05-02T14:42:21Z","cross_cats_sorted":["cs.AI","cs.SY"],"title_canon_sha256":"fefa709cf166a3f414455bd286f5360fe56394108709ffa329566bf170a26aeb","abstract_canon_sha256":"04c3cfc99a6497f7fe319c037bba78642569501d3abc76e64f281c47b1fd0d8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:27.376340Z","signature_b64":"IQLYzgV5eFrVrqsTDxdfvXdSUJ4mWk50PvV1V/AIAmnkfX1RnkLcM/AcRAYsEU84ek4626x99rXgfoCum+vfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e15cd43475c4d4ef9b8c4eb1cfd7e48a6f075303dfb7d3dba0362e4aefc4dc42","last_reissued_at":"2026-07-05T08:25:27.375865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:27.375865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixed-Integer Optimal Control via Reinforcement Learning: A Case Study on Hybrid Electric Vehicle Energy Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY"],"primary_cat":"eess.SY","authors_text":"Jinming Xu, Nasser Lashgarian Azad, Yuan Lin","submitted_at":"2023-05-02T14:42:21Z","abstract_excerpt":"Many optimal control problems require the simultaneous output of discrete and continuous control variables. These problems are usually formulated as mixed-integer optimal control (MIOC) problems, which are challenging to solve due to the complexity of the solution space. Numerical methods such as branch-and-bound are computationally expensive and undesirable for real-time control. This paper proposes a novel hybrid-action reinforcement learning (HARL) algorithm, twin delayed deep deterministic actor-Q (TD3AQ), for MIOC problems. TD3AQ combines the advantages of both actor-critic and Q-learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01461","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.01461/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2305.01461","created_at":"2026-07-05T08:25:27.375928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01461v3","created_at":"2026-07-05T08:25:27.375928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01461","created_at":"2026-07-05T08:25:27.375928+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FONINDVYTKO","created_at":"2026-07-05T08:25:27.375928+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FONINDVYTKO7G4M","created_at":"2026-07-05T08:25:27.375928+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FONINDV","created_at":"2026-07-05T08:25:27.375928+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/4FONINDVYTKO7G4MJ2Y47V7ERJ","json":"https://pith.science/pith/4FONINDVYTKO7G4MJ2Y47V7ERJ.json","graph_json":"https://pith.science/api/pith-number/4FONINDVYTKO7G4MJ2Y47V7ERJ/graph.json","events_json":"https://pith.science/api/pith-number/4FONINDVYTKO7G4MJ2Y47V7ERJ/events.json","paper":"https://pith.science/paper/4FONINDV"},"agent_actions":{"view_html":"https://pith.science/pith/4FONINDVYTKO7G4MJ2Y47V7ERJ","download_json":"https://pith.science/pith/4FONINDVYTKO7G4MJ2Y47V7ERJ.json","view_paper":"https://pith.science/paper/4FONINDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01461&json=true","fetch_graph":"https://pith.science/api/pith-number/4FONINDVYTKO7G4MJ2Y47V7ERJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4FONINDVYTKO7G4MJ2Y47V7ERJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FONINDVYTKO7G4MJ2Y47V7ERJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FONINDVYTKO7G4MJ2Y47V7ERJ/action/storage_attestation","attest_author":"https://pith.science/pith/4FONINDVYTKO7G4MJ2Y47V7ERJ/action/author_attestation","sign_citation":"https://pith.science/pith/4FONINDVYTKO7G4MJ2Y47V7ERJ/action/citation_signature","submit_replication":"https://pith.science/pith/4FONINDVYTKO7G4MJ2Y47V7ERJ/action/replication_record"}},"created_at":"2026-07-05T08:25:27.375928+00:00","updated_at":"2026-07-05T08:25:27.375928+00:00"}