{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OQFKJQUGOS2IBSMX6LIBGHXAHV","short_pith_number":"pith:OQFKJQUG","schema_version":"1.0","canonical_sha256":"740aa4c28674b480c997f2d0131ee03d49e712335899217f2d743556d1693098","source":{"kind":"arxiv","id":"1704.02532","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning framework for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"stat.ML","authors_text":"Ahmad El Sallab, Etienne Perot, Mohammed Abdou, Senthil Yogamani","submitted_at":"2017-04-08T20:04:03Z","abstract_excerpt":"Reinforcement learning is considered to be a strong AI paradigm which can be used to teach machines through interaction with the environment and learning from their mistakes. Despite its perceived utility, it has not yet been successfully applied in automotive applications. Motivated by the successful demonstrations of learning of Atari games and Go by Google DeepMind, we propose a framework for autonomous driving using deep reinforcement learning. This is of particular relevance as it is difficult to pose autonomous driving as a supervised learning problem due to strong interactions with the "},"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":"1704.02532","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2017-04-08T20:04:03Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"77a333fc5f55f1655cf9bea1b173e5a8960dd54e8446a443ab6d2b6caa9fc7ad","abstract_canon_sha256":"81b63beefd9e6343d2437a9274d09e1cb9a16a031c9b4a32b550e9bd39fbcd67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:45.225970Z","signature_b64":"b/ff4kZU7b7qeeS83AWVHbKXW9AiVP2kE34NucGbZeE6ajFouJW/TsblNh3yh1OBpr/WzIwvpyJB8VsRSI2cDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"740aa4c28674b480c997f2d0131ee03d49e712335899217f2d743556d1693098","last_reissued_at":"2026-05-18T00:46:45.225239Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:45.225239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning framework for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"stat.ML","authors_text":"Ahmad El Sallab, Etienne Perot, Mohammed Abdou, Senthil Yogamani","submitted_at":"2017-04-08T20:04:03Z","abstract_excerpt":"Reinforcement learning is considered to be a strong AI paradigm which can be used to teach machines through interaction with the environment and learning from their mistakes. Despite its perceived utility, it has not yet been successfully applied in automotive applications. Motivated by the successful demonstrations of learning of Atari games and Go by Google DeepMind, we propose a framework for autonomous driving using deep reinforcement learning. This is of particular relevance as it is difficult to pose autonomous driving as a supervised learning problem due to strong interactions with the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02532","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":""},"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":"1704.02532","created_at":"2026-05-18T00:46:45.225372+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.02532v1","created_at":"2026-05-18T00:46:45.225372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02532","created_at":"2026-05-18T00:46:45.225372+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQFKJQUGOS2I","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQFKJQUGOS2IBSMX","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQFKJQUG","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2506.14648","citing_title":"SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18246","citing_title":"Privacy Preserving Reinforcement Learning with One-Sided Feedback","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10974","citing_title":"Robust Adversarial Policy Optimization Under Dynamics Uncertainty","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQFKJQUGOS2IBSMX6LIBGHXAHV","json":"https://pith.science/pith/OQFKJQUGOS2IBSMX6LIBGHXAHV.json","graph_json":"https://pith.science/api/pith-number/OQFKJQUGOS2IBSMX6LIBGHXAHV/graph.json","events_json":"https://pith.science/api/pith-number/OQFKJQUGOS2IBSMX6LIBGHXAHV/events.json","paper":"https://pith.science/paper/OQFKJQUG"},"agent_actions":{"view_html":"https://pith.science/pith/OQFKJQUGOS2IBSMX6LIBGHXAHV","download_json":"https://pith.science/pith/OQFKJQUGOS2IBSMX6LIBGHXAHV.json","view_paper":"https://pith.science/paper/OQFKJQUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.02532&json=true","fetch_graph":"https://pith.science/api/pith-number/OQFKJQUGOS2IBSMX6LIBGHXAHV/graph.json","fetch_events":"https://pith.science/api/pith-number/OQFKJQUGOS2IBSMX6LIBGHXAHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQFKJQUGOS2IBSMX6LIBGHXAHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQFKJQUGOS2IBSMX6LIBGHXAHV/action/storage_attestation","attest_author":"https://pith.science/pith/OQFKJQUGOS2IBSMX6LIBGHXAHV/action/author_attestation","sign_citation":"https://pith.science/pith/OQFKJQUGOS2IBSMX6LIBGHXAHV/action/citation_signature","submit_replication":"https://pith.science/pith/OQFKJQUGOS2IBSMX6LIBGHXAHV/action/replication_record"}},"created_at":"2026-05-18T00:46:45.225372+00:00","updated_at":"2026-05-18T00:46:45.225372+00:00"}