{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ELQYQOS2U3YYMWVUZHSYMOU556","short_pith_number":"pith:ELQYQOS2","schema_version":"1.0","canonical_sha256":"22e1883a5aa6f1865ab4c9e5863a9def83b1bdef2a0d7ae7f7d63e60a999e996","source":{"kind":"arxiv","id":"2601.18783","version":2},"attestation_state":"computed","paper":{"title":"Multi-Objective Reinforcement Learning for Tactical Decision Making for Trucks in Highway Traffic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Deepthi Pathare, Leo Laine, Morteza Haghir Chehreghani","submitted_at":"2026-01-26T18:50:21Z","abstract_excerpt":"Balancing safety, efficiency, and operational costs in highway driving poses a challenging decision-making problem for heavy-duty vehicles. A central difficulty is that conventional scalar reward formulations, obtained by aggregating these competing objectives, often obscure the structure of their trade-offs. We present a Proximal Policy Optimization based multi-objective reinforcement learning framework that learns a set of policies explicitly representing these trade-offs and evaluates it on a scalable simulation platform for tactical decision making in trucks. The proposed approach learns a"},"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":"2601.18783","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T18:50:21Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"87ea42ec4bff746056e1989ccba59cb7a76b5d807f3d7298d331f38a2ca7ca12","abstract_canon_sha256":"c12a98104253350db8e178e828bcc19482f8625ed744cae82c1f609a1f9104d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:50.115206Z","signature_b64":"Ddq2f2WBLvRtb8Vhl1rVRz8P3wqDNP7CMKs3bukegZzWy/jl/efwxRAg02g2dXyJUyWEgYfAQihFSf5FgGcUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22e1883a5aa6f1865ab4c9e5863a9def83b1bdef2a0d7ae7f7d63e60a999e996","last_reissued_at":"2026-06-02T02:04:50.114695Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:50.114695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Objective Reinforcement Learning for Tactical Decision Making for Trucks in Highway Traffic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Deepthi Pathare, Leo Laine, Morteza Haghir Chehreghani","submitted_at":"2026-01-26T18:50:21Z","abstract_excerpt":"Balancing safety, efficiency, and operational costs in highway driving poses a challenging decision-making problem for heavy-duty vehicles. A central difficulty is that conventional scalar reward formulations, obtained by aggregating these competing objectives, often obscure the structure of their trade-offs. We present a Proximal Policy Optimization based multi-objective reinforcement learning framework that learns a set of policies explicitly representing these trade-offs and evaluates it on a scalable simulation platform for tactical decision making in trucks. The proposed approach learns a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18783","kind":"arxiv","version":2},"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/2601.18783/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":"2601.18783","created_at":"2026-06-02T02:04:50.114761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.18783v2","created_at":"2026-06-02T02:04:50.114761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18783","created_at":"2026-06-02T02:04:50.114761+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELQYQOS2U3YY","created_at":"2026-06-02T02:04:50.114761+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELQYQOS2U3YYMWVU","created_at":"2026-06-02T02:04:50.114761+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELQYQOS2","created_at":"2026-06-02T02:04:50.114761+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/ELQYQOS2U3YYMWVUZHSYMOU556","json":"https://pith.science/pith/ELQYQOS2U3YYMWVUZHSYMOU556.json","graph_json":"https://pith.science/api/pith-number/ELQYQOS2U3YYMWVUZHSYMOU556/graph.json","events_json":"https://pith.science/api/pith-number/ELQYQOS2U3YYMWVUZHSYMOU556/events.json","paper":"https://pith.science/paper/ELQYQOS2"},"agent_actions":{"view_html":"https://pith.science/pith/ELQYQOS2U3YYMWVUZHSYMOU556","download_json":"https://pith.science/pith/ELQYQOS2U3YYMWVUZHSYMOU556.json","view_paper":"https://pith.science/paper/ELQYQOS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.18783&json=true","fetch_graph":"https://pith.science/api/pith-number/ELQYQOS2U3YYMWVUZHSYMOU556/graph.json","fetch_events":"https://pith.science/api/pith-number/ELQYQOS2U3YYMWVUZHSYMOU556/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELQYQOS2U3YYMWVUZHSYMOU556/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELQYQOS2U3YYMWVUZHSYMOU556/action/storage_attestation","attest_author":"https://pith.science/pith/ELQYQOS2U3YYMWVUZHSYMOU556/action/author_attestation","sign_citation":"https://pith.science/pith/ELQYQOS2U3YYMWVUZHSYMOU556/action/citation_signature","submit_replication":"https://pith.science/pith/ELQYQOS2U3YYMWVUZHSYMOU556/action/replication_record"}},"created_at":"2026-06-02T02:04:50.114761+00:00","updated_at":"2026-06-02T02:04:50.114761+00:00"}