{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3237V4NCPREH4MMEEA2HBXUL6Z","short_pith_number":"pith:3237V4NC","schema_version":"1.0","canonical_sha256":"deb7faf1a27c487e3184203470de8bf640a965651bd4a6d83705e04aa99454c2","source":{"kind":"arxiv","id":"2205.12128","version":1},"attestation_state":"computed","paper":{"title":"Learning to Drive Using Sparse Imitation Reinforcement Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alper Yilmaz, Yuci Han","submitted_at":"2022-05-24T15:03:11Z","abstract_excerpt":"In this paper, we propose Sparse Imitation Reinforcement Learning (SIRL), a hybrid end-to-end control policy that combines the sparse expert driving knowledge with reinforcement learning (RL) policy for autonomous driving (AD) task in CARLA simulation environment. The sparse expert is designed based on hand-crafted rules which is suboptimal but provides a risk-averse strategy by enforcing experience for critical scenarios such as pedestrian and vehicle avoidance, and traffic light detection. As it has been demonstrated, training a RL agent from scratch is data-inefficient and time consuming pa"},"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":"2205.12128","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-24T15:03:11Z","cross_cats_sorted":[],"title_canon_sha256":"8e66097b6704ae1de510f96c7a1e039abf46ea8b53585acf41981944fa33c122","abstract_canon_sha256":"2a97b5b1797809f9dd31efd60a7875d8fa5df364c9fe5d03616561c2042c8d89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:11.602934Z","signature_b64":"UNdlTriIEld99BClFiqbFPQLLjN0WHtc7xdAPBqRK4fkA8ihXNcBq/LfvwKG7DMU8eZvzVLwOzwrUZ1sXElYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"deb7faf1a27c487e3184203470de8bf640a965651bd4a6d83705e04aa99454c2","last_reissued_at":"2026-07-05T04:26:11.602572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:11.602572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Drive Using Sparse Imitation Reinforcement Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alper Yilmaz, Yuci Han","submitted_at":"2022-05-24T15:03:11Z","abstract_excerpt":"In this paper, we propose Sparse Imitation Reinforcement Learning (SIRL), a hybrid end-to-end control policy that combines the sparse expert driving knowledge with reinforcement learning (RL) policy for autonomous driving (AD) task in CARLA simulation environment. The sparse expert is designed based on hand-crafted rules which is suboptimal but provides a risk-averse strategy by enforcing experience for critical scenarios such as pedestrian and vehicle avoidance, and traffic light detection. As it has been demonstrated, training a RL agent from scratch is data-inefficient and time consuming pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12128","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/2205.12128/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":"2205.12128","created_at":"2026-07-05T04:26:11.602621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12128v1","created_at":"2026-07-05T04:26:11.602621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12128","created_at":"2026-07-05T04:26:11.602621+00:00"},{"alias_kind":"pith_short_12","alias_value":"3237V4NCPREH","created_at":"2026-07-05T04:26:11.602621+00:00"},{"alias_kind":"pith_short_16","alias_value":"3237V4NCPREH4MME","created_at":"2026-07-05T04:26:11.602621+00:00"},{"alias_kind":"pith_short_8","alias_value":"3237V4NC","created_at":"2026-07-05T04:26:11.602621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08221","citing_title":"A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3237V4NCPREH4MMEEA2HBXUL6Z","json":"https://pith.science/pith/3237V4NCPREH4MMEEA2HBXUL6Z.json","graph_json":"https://pith.science/api/pith-number/3237V4NCPREH4MMEEA2HBXUL6Z/graph.json","events_json":"https://pith.science/api/pith-number/3237V4NCPREH4MMEEA2HBXUL6Z/events.json","paper":"https://pith.science/paper/3237V4NC"},"agent_actions":{"view_html":"https://pith.science/pith/3237V4NCPREH4MMEEA2HBXUL6Z","download_json":"https://pith.science/pith/3237V4NCPREH4MMEEA2HBXUL6Z.json","view_paper":"https://pith.science/paper/3237V4NC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12128&json=true","fetch_graph":"https://pith.science/api/pith-number/3237V4NCPREH4MMEEA2HBXUL6Z/graph.json","fetch_events":"https://pith.science/api/pith-number/3237V4NCPREH4MMEEA2HBXUL6Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3237V4NCPREH4MMEEA2HBXUL6Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3237V4NCPREH4MMEEA2HBXUL6Z/action/storage_attestation","attest_author":"https://pith.science/pith/3237V4NCPREH4MMEEA2HBXUL6Z/action/author_attestation","sign_citation":"https://pith.science/pith/3237V4NCPREH4MMEEA2HBXUL6Z/action/citation_signature","submit_replication":"https://pith.science/pith/3237V4NCPREH4MMEEA2HBXUL6Z/action/replication_record"}},"created_at":"2026-07-05T04:26:11.602621+00:00","updated_at":"2026-07-05T04:26:11.602621+00:00"}