{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LG2YSDOU3LZXJ5V7A7PW6K5QVW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c746a81cb5934d2ed5bfae366402d323ca31913bc58cca6df4400be3a29d724b","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T01:31:14Z","title_canon_sha256":"0e07322992faa61ff7b08cac63c41da4d5f5947c99492ca45022e7ad0c920563"},"schema_version":"1.0","source":{"id":"2503.23650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23650","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23650v1","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23650","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"LG2YSDOU3LZX","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_16","alias_value":"LG2YSDOU3LZXJ5V7","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_8","alias_value":"LG2YSDOU","created_at":"2026-07-05T10:41:57Z"}],"graph_snapshots":[{"event_id":"sha256:80e6748f4d947ab896239c2b2dd9f1281c8c08b95259e860128fc5e9cb7fb33a","target":"graph","created_at":"2026-07-05T10:41:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.23650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL), with its ability to explore and optimize policies in complex, dynamic decision-making tasks, has emerged as a promising approach to addressing motion planning (MoP) challenges in autonomous driving (AD). Despite rapid advancements in RL and AD, a systematic description and interpretation of the RL design process tailored to diverse driving tasks remains underdeveloped. This survey provides a comprehensive review of RL-based MoP for AD, focusing on lessons from task-specific perspectives. We first outline the fundamentals of RL methodologies, and then survey their a","authors_text":"Bo Leng, Dimitar Filev, Guizhe Jin, Ilya Kolmanovsky, Jia Hu, Lu Xiong, Nan Li, Ran Yu, Wei Han, Zhiwen Chen, Zhuoren Li","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T01:31:14Z","title":"A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23650","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a49befde87debc68b0df55a4b7f3384e0247b135287f5d1b291086502dd6a5fe","target":"record","created_at":"2026-07-05T10:41:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c746a81cb5934d2ed5bfae366402d323ca31913bc58cca6df4400be3a29d724b","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T01:31:14Z","title_canon_sha256":"0e07322992faa61ff7b08cac63c41da4d5f5947c99492ca45022e7ad0c920563"},"schema_version":"1.0","source":{"id":"2503.23650","kind":"arxiv","version":1}},"canonical_sha256":"59b5890dd4daf374f6bf07df6f2bb0ad9cda69c1c5ad8db968a80faa3e28a3fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59b5890dd4daf374f6bf07df6f2bb0ad9cda69c1c5ad8db968a80faa3e28a3fc","first_computed_at":"2026-07-05T10:41:57.222727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:57.222727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6NYukxiWa9VvDi2dp4hgxC+vu75KYtn5IogJP7N1zCU5HUxgtXXvxrrytym0bmEOCZSU0y/XeMKLuRo4e65VBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:57.223212Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a49befde87debc68b0df55a4b7f3384e0247b135287f5d1b291086502dd6a5fe","sha256:80e6748f4d947ab896239c2b2dd9f1281c8c08b95259e860128fc5e9cb7fb33a"],"state_sha256":"5980e64f64e473f8d595120b2ce8f64dc5d82f9573758b839b06f6271a252ca4"}