{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KKZGKDKBGHTLX4LYA6PFZKS454","short_pith_number":"pith:KKZGKDKB","schema_version":"1.0","canonical_sha256":"52b2650d4131e6bbf178079e5caa5cef015f3317112da25f05ccd199d4d88012","source":{"kind":"arxiv","id":"2011.04697","version":1},"attestation_state":"computed","paper":{"title":"Behavior Planning at Urban Intersections through Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jeff Schneider, John M. Dolan, Zhiqian Qiao","submitted_at":"2020-11-09T19:23:26Z","abstract_excerpt":"For autonomous vehicles, effective behavior planning is crucial to ensure safety of the ego car. In many urban scenarios, it is hard to create sufficiently general heuristic rules, especially for challenging scenarios that some new human drivers find difficult. In this work, we propose a behavior planning structure based on reinforcement learning (RL) which is capable of performing autonomous vehicle behavior planning with a hierarchical structure in simulated urban environments. Application of the hierarchical structure allows the various layers of the behavior planning system to be satisfied"},"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":"2011.04697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-09T19:23:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e1458400474525cb8b9190db32f9c9c0aa6be5954501d3a124fefcd99abb014","abstract_canon_sha256":"19cce2c60dc9bfc9225e5b8f9993e723fbdc4e95c0a7e029f269b7d9b2804bad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:39.411050Z","signature_b64":"KYc7Vc2hmV6o7CSbnXIMoMrRdAn89NEGvULZowHKNM5Bp3jOjnzstV2eRzkOVXp0mQQScrSJIEZI34jUnDVJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52b2650d4131e6bbf178079e5caa5cef015f3317112da25f05ccd199d4d88012","last_reissued_at":"2026-07-05T01:50:39.410672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:39.410672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Behavior Planning at Urban Intersections through Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jeff Schneider, John M. Dolan, Zhiqian Qiao","submitted_at":"2020-11-09T19:23:26Z","abstract_excerpt":"For autonomous vehicles, effective behavior planning is crucial to ensure safety of the ego car. In many urban scenarios, it is hard to create sufficiently general heuristic rules, especially for challenging scenarios that some new human drivers find difficult. In this work, we propose a behavior planning structure based on reinforcement learning (RL) which is capable of performing autonomous vehicle behavior planning with a hierarchical structure in simulated urban environments. Application of the hierarchical structure allows the various layers of the behavior planning system to be satisfied"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04697","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/2011.04697/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":"2011.04697","created_at":"2026-07-05T01:50:39.410727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.04697v1","created_at":"2026-07-05T01:50:39.410727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04697","created_at":"2026-07-05T01:50:39.410727+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKZGKDKBGHTL","created_at":"2026-07-05T01:50:39.410727+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKZGKDKBGHTLX4LY","created_at":"2026-07-05T01:50:39.410727+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKZGKDKB","created_at":"2026-07-05T01:50:39.410727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16336","citing_title":"Goal-conditioned Hierarchical Reinforcement Learning for Sample-efficient and Safe Autonomous Driving at Intersections","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKZGKDKBGHTLX4LYA6PFZKS454","json":"https://pith.science/pith/KKZGKDKBGHTLX4LYA6PFZKS454.json","graph_json":"https://pith.science/api/pith-number/KKZGKDKBGHTLX4LYA6PFZKS454/graph.json","events_json":"https://pith.science/api/pith-number/KKZGKDKBGHTLX4LYA6PFZKS454/events.json","paper":"https://pith.science/paper/KKZGKDKB"},"agent_actions":{"view_html":"https://pith.science/pith/KKZGKDKBGHTLX4LYA6PFZKS454","download_json":"https://pith.science/pith/KKZGKDKBGHTLX4LYA6PFZKS454.json","view_paper":"https://pith.science/paper/KKZGKDKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.04697&json=true","fetch_graph":"https://pith.science/api/pith-number/KKZGKDKBGHTLX4LYA6PFZKS454/graph.json","fetch_events":"https://pith.science/api/pith-number/KKZGKDKBGHTLX4LYA6PFZKS454/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKZGKDKBGHTLX4LYA6PFZKS454/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKZGKDKBGHTLX4LYA6PFZKS454/action/storage_attestation","attest_author":"https://pith.science/pith/KKZGKDKBGHTLX4LYA6PFZKS454/action/author_attestation","sign_citation":"https://pith.science/pith/KKZGKDKBGHTLX4LYA6PFZKS454/action/citation_signature","submit_replication":"https://pith.science/pith/KKZGKDKBGHTLX4LYA6PFZKS454/action/replication_record"}},"created_at":"2026-07-05T01:50:39.410727+00:00","updated_at":"2026-07-05T01:50:39.410727+00:00"}