{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JKVJIHE3MHSZLRGOER4EIV4FJV","short_pith_number":"pith:JKVJIHE3","schema_version":"1.0","canonical_sha256":"4aaa941c9b61e595c4ce24784457854d503039f55711d172acd8a4884c44f30b","source":{"kind":"arxiv","id":"1904.09503","version":2},"attestation_state":"computed","paper":{"title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bodi Yuan, Jianyu Chen, Masayoshi Tomizuka","submitted_at":"2019-04-20T22:02:45Z","abstract_excerpt":"Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions. Current decision making methods are mostly manually designing the driving policy, which might result in sub-optimal solutions and is expensive to develop, generalize and maintain at scale. On the other hand, with reinforcement learning (RL), a policy can be learned and improved automatically without any manual designs. However, current RL methods generally do not work well on complex urban scenarios. In this paper, we propose a framework to enable model-free deep reinforcement lea"},"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":"1904.09503","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-20T22:02:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"a0d76b40973af4dadcd0d1c71e9ddfb4b54e3b37503e7756784f77638722edf3","abstract_canon_sha256":"352ceb42d338d804ea32c5f332ea8f8366ad1cb90f274641ba1657fcecf292d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:44.926341Z","signature_b64":"MNunEbfo5XSazoAE3q1+3QuNv04uHK08R4017CEHnq6PSO80OHqZZh5/SIJ0tat2bBLF6N7HxMZJc8mHotg0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aaa941c9b61e595c4ce24784457854d503039f55711d172acd8a4884c44f30b","last_reissued_at":"2026-07-05T00:13:44.925874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:44.925874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bodi Yuan, Jianyu Chen, Masayoshi Tomizuka","submitted_at":"2019-04-20T22:02:45Z","abstract_excerpt":"Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions. Current decision making methods are mostly manually designing the driving policy, which might result in sub-optimal solutions and is expensive to develop, generalize and maintain at scale. On the other hand, with reinforcement learning (RL), a policy can be learned and improved automatically without any manual designs. However, current RL methods generally do not work well on complex urban scenarios. In this paper, we propose a framework to enable model-free deep reinforcement lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09503","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/1904.09503/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":"1904.09503","created_at":"2026-07-05T00:13:44.925943+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.09503v2","created_at":"2026-07-05T00:13:44.925943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09503","created_at":"2026-07-05T00:13:44.925943+00:00"},{"alias_kind":"pith_short_12","alias_value":"JKVJIHE3MHSZ","created_at":"2026-07-05T00:13:44.925943+00:00"},{"alias_kind":"pith_short_16","alias_value":"JKVJIHE3MHSZLRGO","created_at":"2026-07-05T00:13:44.925943+00:00"},{"alias_kind":"pith_short_8","alias_value":"JKVJIHE3","created_at":"2026-07-05T00:13:44.925943+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/JKVJIHE3MHSZLRGOER4EIV4FJV","json":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV.json","graph_json":"https://pith.science/api/pith-number/JKVJIHE3MHSZLRGOER4EIV4FJV/graph.json","events_json":"https://pith.science/api/pith-number/JKVJIHE3MHSZLRGOER4EIV4FJV/events.json","paper":"https://pith.science/paper/JKVJIHE3"},"agent_actions":{"view_html":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV","download_json":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV.json","view_paper":"https://pith.science/paper/JKVJIHE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.09503&json=true","fetch_graph":"https://pith.science/api/pith-number/JKVJIHE3MHSZLRGOER4EIV4FJV/graph.json","fetch_events":"https://pith.science/api/pith-number/JKVJIHE3MHSZLRGOER4EIV4FJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV/action/storage_attestation","attest_author":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV/action/author_attestation","sign_citation":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV/action/citation_signature","submit_replication":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV/action/replication_record"}},"created_at":"2026-07-05T00:13:44.925943+00:00","updated_at":"2026-07-05T00:13:44.925943+00:00"}