{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7FOCKPVLAUM3CM6DXBNH6VHAKE","short_pith_number":"pith:7FOCKPVL","schema_version":"1.0","canonical_sha256":"f95c253eab0519b133c3b85a7f54e05124d2a530e34f4ef4735c20e6051ee7e9","source":{"kind":"arxiv","id":"2105.11640","version":2},"attestation_state":"computed","paper":{"title":"Safe Model-based Off-policy Reinforcement Learning for Eco-Driving in Connected and Automated Hybrid Electric Vehicles","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Marcello Canova, Nicola Pivaro, Shobhit Gupta, Zhaoxuan Zhu","submitted_at":"2021-05-25T03:41:29Z","abstract_excerpt":"Connected and Automated Hybrid Electric Vehicles have the potential to reduce fuel consumption and travel time in real-world driving conditions. The eco-driving problem seeks to design optimal speed and power usage profiles based upon look-ahead information from connectivity and advanced mapping features. Recently, Deep Reinforcement Learning (DRL) has been applied to the eco-driving problem. While the previous studies synthesize simulators and model-free DRL to reduce online computation, this work proposes a Safe Off-policy Model-Based Reinforcement Learning algorithm for the eco-driving prob"},"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":"2105.11640","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-25T03:41:29Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"577b23cd2e71430a95728c6c23fca3d673bc0c8a1a8b4dbd2727441002bdc427","abstract_canon_sha256":"fb2eef47f846d3913a86c6037a0710e47af8a86ec613007308aca3c4f9d3a65c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:28.565261Z","signature_b64":"vqYpZeltjlvDSUtWAm4Ep0tZOHNVrtTnboo/F0Y6szp58hbmCCG5Eakn1lxhICMJ6NDM4n3KEFMkhlGcWJcEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f95c253eab0519b133c3b85a7f54e05124d2a530e34f4ef4735c20e6051ee7e9","last_reissued_at":"2026-07-05T03:52:28.564663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:28.564663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Model-based Off-policy Reinforcement Learning for Eco-Driving in Connected and Automated Hybrid Electric Vehicles","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Marcello Canova, Nicola Pivaro, Shobhit Gupta, Zhaoxuan Zhu","submitted_at":"2021-05-25T03:41:29Z","abstract_excerpt":"Connected and Automated Hybrid Electric Vehicles have the potential to reduce fuel consumption and travel time in real-world driving conditions. The eco-driving problem seeks to design optimal speed and power usage profiles based upon look-ahead information from connectivity and advanced mapping features. Recently, Deep Reinforcement Learning (DRL) has been applied to the eco-driving problem. While the previous studies synthesize simulators and model-free DRL to reduce online computation, this work proposes a Safe Off-policy Model-Based Reinforcement Learning algorithm for the eco-driving prob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11640","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/2105.11640/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":"2105.11640","created_at":"2026-07-05T03:52:28.564729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.11640v2","created_at":"2026-07-05T03:52:28.564729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11640","created_at":"2026-07-05T03:52:28.564729+00:00"},{"alias_kind":"pith_short_12","alias_value":"7FOCKPVLAUM3","created_at":"2026-07-05T03:52:28.564729+00:00"},{"alias_kind":"pith_short_16","alias_value":"7FOCKPVLAUM3CM6D","created_at":"2026-07-05T03:52:28.564729+00:00"},{"alias_kind":"pith_short_8","alias_value":"7FOCKPVL","created_at":"2026-07-05T03:52:28.564729+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/7FOCKPVLAUM3CM6DXBNH6VHAKE","json":"https://pith.science/pith/7FOCKPVLAUM3CM6DXBNH6VHAKE.json","graph_json":"https://pith.science/api/pith-number/7FOCKPVLAUM3CM6DXBNH6VHAKE/graph.json","events_json":"https://pith.science/api/pith-number/7FOCKPVLAUM3CM6DXBNH6VHAKE/events.json","paper":"https://pith.science/paper/7FOCKPVL"},"agent_actions":{"view_html":"https://pith.science/pith/7FOCKPVLAUM3CM6DXBNH6VHAKE","download_json":"https://pith.science/pith/7FOCKPVLAUM3CM6DXBNH6VHAKE.json","view_paper":"https://pith.science/paper/7FOCKPVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.11640&json=true","fetch_graph":"https://pith.science/api/pith-number/7FOCKPVLAUM3CM6DXBNH6VHAKE/graph.json","fetch_events":"https://pith.science/api/pith-number/7FOCKPVLAUM3CM6DXBNH6VHAKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7FOCKPVLAUM3CM6DXBNH6VHAKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7FOCKPVLAUM3CM6DXBNH6VHAKE/action/storage_attestation","attest_author":"https://pith.science/pith/7FOCKPVLAUM3CM6DXBNH6VHAKE/action/author_attestation","sign_citation":"https://pith.science/pith/7FOCKPVLAUM3CM6DXBNH6VHAKE/action/citation_signature","submit_replication":"https://pith.science/pith/7FOCKPVLAUM3CM6DXBNH6VHAKE/action/replication_record"}},"created_at":"2026-07-05T03:52:28.564729+00:00","updated_at":"2026-07-05T03:52:28.564729+00:00"}