{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KPRQNP7Y5OMZDAL6UTB7CH5FA5","short_pith_number":"pith:KPRQNP7Y","schema_version":"1.0","canonical_sha256":"53e306bff8eb9991817ea4c3f11fa507621da3d8f63a7c885fc144622a6a15d1","source":{"kind":"arxiv","id":"2405.11331","version":3},"attestation_state":"computed","paper":{"title":"Generalized Multi-Objective Reinforcement Learning with Envelope Updates in URLLC-enabled Vehicular Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.NI"],"primary_cat":"cs.LG","authors_text":"Hina Tabassum, Zijiang Yan","submitted_at":"2024-05-18T16:31:32Z","abstract_excerpt":"We develop a novel multi-objective reinforcement learning (MORL) framework to jointly optimize wireless network selection and autonomous driving policies in a multi-band vehicular network operating on conventional sub-6GHz spectrum and Terahertz frequencies. The proposed framework is designed to 1. maximize the traffic flow and minimize collisions by controlling the vehicle's motion dynamics (i.e., speed and acceleration), and 2. enhance the ultra-reliable low-latency communication (URLLC) while minimizing handoffs (HOs). We cast this problem as a multi-objective Markov Decision Process (MOMDP"},"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":"2405.11331","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-18T16:31:32Z","cross_cats_sorted":["cs.AI","cs.NI"],"title_canon_sha256":"1c2c690e1ed805c0b7a7744df84c721b2ac52a8edba860de18e997db374d5ddb","abstract_canon_sha256":"f021011469acaf912b0dd8197930eb26bd45bf0cb11cb0acef726f1b8f4d5312"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:32.913516Z","signature_b64":"O96nBFVL5vTNEo38lf5UwfTJ00Hm07foZJgb+VS+UGJsRPtwrqdqq3BZKCtrakcdk9k+Xf6Uwp1p8Q1fCkijBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e306bff8eb9991817ea4c3f11fa507621da3d8f63a7c885fc144622a6a15d1","last_reissued_at":"2026-07-05T11:21:32.913040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:32.913040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Multi-Objective Reinforcement Learning with Envelope Updates in URLLC-enabled Vehicular Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.NI"],"primary_cat":"cs.LG","authors_text":"Hina Tabassum, Zijiang Yan","submitted_at":"2024-05-18T16:31:32Z","abstract_excerpt":"We develop a novel multi-objective reinforcement learning (MORL) framework to jointly optimize wireless network selection and autonomous driving policies in a multi-band vehicular network operating on conventional sub-6GHz spectrum and Terahertz frequencies. The proposed framework is designed to 1. maximize the traffic flow and minimize collisions by controlling the vehicle's motion dynamics (i.e., speed and acceleration), and 2. enhance the ultra-reliable low-latency communication (URLLC) while minimizing handoffs (HOs). We cast this problem as a multi-objective Markov Decision Process (MOMDP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11331","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/2405.11331/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":"2405.11331","created_at":"2026-07-05T11:21:32.913114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11331v3","created_at":"2026-07-05T11:21:32.913114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11331","created_at":"2026-07-05T11:21:32.913114+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPRQNP7Y5OMZ","created_at":"2026-07-05T11:21:32.913114+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPRQNP7Y5OMZDAL6","created_at":"2026-07-05T11:21:32.913114+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPRQNP7Y","created_at":"2026-07-05T11:21:32.913114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06532","citing_title":"Hierarchical and Collaborative LLM-Based Control for Multi-UAV Motion and Communication in Integrated Terrestrial and Non-Terrestrial Networks","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPRQNP7Y5OMZDAL6UTB7CH5FA5","json":"https://pith.science/pith/KPRQNP7Y5OMZDAL6UTB7CH5FA5.json","graph_json":"https://pith.science/api/pith-number/KPRQNP7Y5OMZDAL6UTB7CH5FA5/graph.json","events_json":"https://pith.science/api/pith-number/KPRQNP7Y5OMZDAL6UTB7CH5FA5/events.json","paper":"https://pith.science/paper/KPRQNP7Y"},"agent_actions":{"view_html":"https://pith.science/pith/KPRQNP7Y5OMZDAL6UTB7CH5FA5","download_json":"https://pith.science/pith/KPRQNP7Y5OMZDAL6UTB7CH5FA5.json","view_paper":"https://pith.science/paper/KPRQNP7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11331&json=true","fetch_graph":"https://pith.science/api/pith-number/KPRQNP7Y5OMZDAL6UTB7CH5FA5/graph.json","fetch_events":"https://pith.science/api/pith-number/KPRQNP7Y5OMZDAL6UTB7CH5FA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPRQNP7Y5OMZDAL6UTB7CH5FA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPRQNP7Y5OMZDAL6UTB7CH5FA5/action/storage_attestation","attest_author":"https://pith.science/pith/KPRQNP7Y5OMZDAL6UTB7CH5FA5/action/author_attestation","sign_citation":"https://pith.science/pith/KPRQNP7Y5OMZDAL6UTB7CH5FA5/action/citation_signature","submit_replication":"https://pith.science/pith/KPRQNP7Y5OMZDAL6UTB7CH5FA5/action/replication_record"}},"created_at":"2026-07-05T11:21:32.913114+00:00","updated_at":"2026-07-05T11:21:32.913114+00:00"}