{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IMHGHOU7GJN3YLNKEKT5FUH6G5","short_pith_number":"pith:IMHGHOU7","schema_version":"1.0","canonical_sha256":"430e63ba9f325bbc2daa22a7d2d0fe374d88bca1c3ba09b67bb3f395aea29719","source":{"kind":"arxiv","id":"2402.04168","version":2},"attestation_state":"computed","paper":{"title":"Informed Reinforcement Learning for Situation-Aware Traffic Rule Exceptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ahmed Abouelazm, Daniel Bogdoll, Jing Qin, J. Marius Z\\\"ollner, Moritz Nekolla, Tim Joseph","submitted_at":"2024-02-06T17:24:06Z","abstract_excerpt":"Reinforcement Learning is a highly active research field with promising advancements. In the field of autonomous driving, however, often very simple scenarios are being examined. Common approaches use non-interpretable control commands as the action space and unstructured reward designs which lack structure. In this work, we introduce Informed Reinforcement Learning, where a structured rulebook is integrated as a knowledge source. We learn trajectories and asses them with a situation-aware reward design, leading to a dynamic reward which allows the agent to learn situations which require contr"},"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":"2402.04168","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T17:24:06Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"f3123225d12ccd3ddab68568a33bbc72ad9b03791c40f06b739e5be7f9e9b8bc","abstract_canon_sha256":"c59b043675db0e1c3836caa18ce7ff2f7ed59b2d5bf1950f62b0268a124f4f12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:14.539613Z","signature_b64":"stjq30Npl3GU3pt0eq1fVBq0i+6/bNT+LcLLgCo9XItD65UlLOzCa5NBDhUlTeCE2Yuj9BJnNKeDqs/Q46NmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"430e63ba9f325bbc2daa22a7d2d0fe374d88bca1c3ba09b67bb3f395aea29719","last_reissued_at":"2026-07-05T10:58:14.539104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:14.539104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Informed Reinforcement Learning for Situation-Aware Traffic Rule Exceptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ahmed Abouelazm, Daniel Bogdoll, Jing Qin, J. Marius Z\\\"ollner, Moritz Nekolla, Tim Joseph","submitted_at":"2024-02-06T17:24:06Z","abstract_excerpt":"Reinforcement Learning is a highly active research field with promising advancements. In the field of autonomous driving, however, often very simple scenarios are being examined. Common approaches use non-interpretable control commands as the action space and unstructured reward designs which lack structure. In this work, we introduce Informed Reinforcement Learning, where a structured rulebook is integrated as a knowledge source. We learn trajectories and asses them with a situation-aware reward design, leading to a dynamic reward which allows the agent to learn situations which require contr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04168","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/2402.04168/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":"2402.04168","created_at":"2026-07-05T10:58:14.539167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04168v2","created_at":"2026-07-05T10:58:14.539167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04168","created_at":"2026-07-05T10:58:14.539167+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMHGHOU7GJN3","created_at":"2026-07-05T10:58:14.539167+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMHGHOU7GJN3YLNK","created_at":"2026-07-05T10:58:14.539167+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMHGHOU7","created_at":"2026-07-05T10:58:14.539167+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/IMHGHOU7GJN3YLNKEKT5FUH6G5","json":"https://pith.science/pith/IMHGHOU7GJN3YLNKEKT5FUH6G5.json","graph_json":"https://pith.science/api/pith-number/IMHGHOU7GJN3YLNKEKT5FUH6G5/graph.json","events_json":"https://pith.science/api/pith-number/IMHGHOU7GJN3YLNKEKT5FUH6G5/events.json","paper":"https://pith.science/paper/IMHGHOU7"},"agent_actions":{"view_html":"https://pith.science/pith/IMHGHOU7GJN3YLNKEKT5FUH6G5","download_json":"https://pith.science/pith/IMHGHOU7GJN3YLNKEKT5FUH6G5.json","view_paper":"https://pith.science/paper/IMHGHOU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04168&json=true","fetch_graph":"https://pith.science/api/pith-number/IMHGHOU7GJN3YLNKEKT5FUH6G5/graph.json","fetch_events":"https://pith.science/api/pith-number/IMHGHOU7GJN3YLNKEKT5FUH6G5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMHGHOU7GJN3YLNKEKT5FUH6G5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMHGHOU7GJN3YLNKEKT5FUH6G5/action/storage_attestation","attest_author":"https://pith.science/pith/IMHGHOU7GJN3YLNKEKT5FUH6G5/action/author_attestation","sign_citation":"https://pith.science/pith/IMHGHOU7GJN3YLNKEKT5FUH6G5/action/citation_signature","submit_replication":"https://pith.science/pith/IMHGHOU7GJN3YLNKEKT5FUH6G5/action/replication_record"}},"created_at":"2026-07-05T10:58:14.539167+00:00","updated_at":"2026-07-05T10:58:14.539167+00:00"}