{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BZMZCDYFZQB4MJWBO3SSQAJCPN","short_pith_number":"pith:BZMZCDYF","schema_version":"1.0","canonical_sha256":"0e59910f05cc03c626c176e52801227b649a4e6b09cc135fd12b1bd2bf0ddc13","source":{"kind":"arxiv","id":"2509.08221","version":1},"attestation_state":"computed","paper":{"title":"A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Elahe Delavari, Feeza Khan Khanzada, Jaerock Kwon","submitted_at":"2025-09-10T01:38:55Z","abstract_excerpt":"Autonomous-driving research has recently embraced deep Reinforcement Learning (RL) as a promising framework for data-driven decision making, yet a clear picture of how these algorithms are currently employed, benchmarked and evaluated is still missing. This survey fills that gap by systematically analysing around 100 peer-reviewed papers that train, test or validate RL policies inside the open-source CARLA simulator. We first categorize the literature by algorithmic family model-free, model-based, hierarchical, and hybrid and quantify their prevalence, highlighting that more than 80% of existi"},"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":"2509.08221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-10T01:38:55Z","cross_cats_sorted":[],"title_canon_sha256":"35b2c76d364a48e9929341144e232802e5e21446957e1833f7613e5b736d8a03","abstract_canon_sha256":"089c7f20355f4f6d34530d231f132c86a8e798064d69539dc86478e026c9234c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:25.347165Z","signature_b64":"Ir1f4AcxQw7n4WwP2RUYY5CgCBOJSgWq58PsDcSRwUnK/pFS9BB3WUsKe+9C1rH32cAV4OxlK7o7S8K4UNNuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e59910f05cc03c626c176e52801227b649a4e6b09cc135fd12b1bd2bf0ddc13","last_reissued_at":"2026-07-05T12:08:25.346620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:25.346620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Elahe Delavari, Feeza Khan Khanzada, Jaerock Kwon","submitted_at":"2025-09-10T01:38:55Z","abstract_excerpt":"Autonomous-driving research has recently embraced deep Reinforcement Learning (RL) as a promising framework for data-driven decision making, yet a clear picture of how these algorithms are currently employed, benchmarked and evaluated is still missing. This survey fills that gap by systematically analysing around 100 peer-reviewed papers that train, test or validate RL policies inside the open-source CARLA simulator. We first categorize the literature by algorithmic family model-free, model-based, hierarchical, and hybrid and quantify their prevalence, highlighting that more than 80% of existi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08221","kind":"arxiv","version":1},"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/2509.08221/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":"2509.08221","created_at":"2026-07-05T12:08:25.346680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08221v1","created_at":"2026-07-05T12:08:25.346680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08221","created_at":"2026-07-05T12:08:25.346680+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZMZCDYFZQB4","created_at":"2026-07-05T12:08:25.346680+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZMZCDYFZQB4MJWB","created_at":"2026-07-05T12:08:25.346680+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZMZCDYF","created_at":"2026-07-05T12:08:25.346680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27994","citing_title":"Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03497","citing_title":"Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZMZCDYFZQB4MJWBO3SSQAJCPN","json":"https://pith.science/pith/BZMZCDYFZQB4MJWBO3SSQAJCPN.json","graph_json":"https://pith.science/api/pith-number/BZMZCDYFZQB4MJWBO3SSQAJCPN/graph.json","events_json":"https://pith.science/api/pith-number/BZMZCDYFZQB4MJWBO3SSQAJCPN/events.json","paper":"https://pith.science/paper/BZMZCDYF"},"agent_actions":{"view_html":"https://pith.science/pith/BZMZCDYFZQB4MJWBO3SSQAJCPN","download_json":"https://pith.science/pith/BZMZCDYFZQB4MJWBO3SSQAJCPN.json","view_paper":"https://pith.science/paper/BZMZCDYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08221&json=true","fetch_graph":"https://pith.science/api/pith-number/BZMZCDYFZQB4MJWBO3SSQAJCPN/graph.json","fetch_events":"https://pith.science/api/pith-number/BZMZCDYFZQB4MJWBO3SSQAJCPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZMZCDYFZQB4MJWBO3SSQAJCPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZMZCDYFZQB4MJWBO3SSQAJCPN/action/storage_attestation","attest_author":"https://pith.science/pith/BZMZCDYFZQB4MJWBO3SSQAJCPN/action/author_attestation","sign_citation":"https://pith.science/pith/BZMZCDYFZQB4MJWBO3SSQAJCPN/action/citation_signature","submit_replication":"https://pith.science/pith/BZMZCDYFZQB4MJWBO3SSQAJCPN/action/replication_record"}},"created_at":"2026-07-05T12:08:25.346680+00:00","updated_at":"2026-07-05T12:08:25.346680+00:00"}