{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IMHGHOU7GJN3YLNKEKT5FUH6G5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c59b043675db0e1c3836caa18ce7ff2f7ed59b2d5bf1950f62b0268a124f4f12","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T17:24:06Z","title_canon_sha256":"f3123225d12ccd3ddab68568a33bbc72ad9b03791c40f06b739e5be7f9e9b8bc"},"schema_version":"1.0","source":{"id":"2402.04168","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04168","created_at":"2026-07-05T10:58:14Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04168v2","created_at":"2026-07-05T10:58:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04168","created_at":"2026-07-05T10:58:14Z"},{"alias_kind":"pith_short_12","alias_value":"IMHGHOU7GJN3","created_at":"2026-07-05T10:58:14Z"},{"alias_kind":"pith_short_16","alias_value":"IMHGHOU7GJN3YLNK","created_at":"2026-07-05T10:58:14Z"},{"alias_kind":"pith_short_8","alias_value":"IMHGHOU7","created_at":"2026-07-05T10:58:14Z"}],"graph_snapshots":[{"event_id":"sha256:8510d3bfb556e018c124d951384cca5e4da3136122c46db97918f3dbdcda473b","target":"graph","created_at":"2026-07-05T10:58:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.04168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ahmed Abouelazm, Daniel Bogdoll, Jing Qin, J. Marius Z\\\"ollner, Moritz Nekolla, Tim Joseph","cross_cats":["cs.CV","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T17:24:06Z","title":"Informed Reinforcement Learning for Situation-Aware Traffic Rule Exceptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04168","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:364582c58f836d12f448d52d0c2d37e040698c83ac87860aeb8f6996bc4fb48a","target":"record","created_at":"2026-07-05T10:58:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c59b043675db0e1c3836caa18ce7ff2f7ed59b2d5bf1950f62b0268a124f4f12","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T17:24:06Z","title_canon_sha256":"f3123225d12ccd3ddab68568a33bbc72ad9b03791c40f06b739e5be7f9e9b8bc"},"schema_version":"1.0","source":{"id":"2402.04168","kind":"arxiv","version":2}},"canonical_sha256":"430e63ba9f325bbc2daa22a7d2d0fe374d88bca1c3ba09b67bb3f395aea29719","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"430e63ba9f325bbc2daa22a7d2d0fe374d88bca1c3ba09b67bb3f395aea29719","first_computed_at":"2026-07-05T10:58:14.539104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:14.539104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"stjq30Npl3GU3pt0eq1fVBq0i+6/bNT+LcLLgCo9XItD65UlLOzCa5NBDhUlTeCE2Yuj9BJnNKeDqs/Q46NmCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:14.539613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04168","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:364582c58f836d12f448d52d0c2d37e040698c83ac87860aeb8f6996bc4fb48a","sha256:8510d3bfb556e018c124d951384cca5e4da3136122c46db97918f3dbdcda473b"],"state_sha256":"037ccf4af9205d8dd8dfa73e378f6beb7afccff946ec9f6eca9cdc2dcff36dab"}