{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OYXTWZQWE4QN776RCQNQJM3BTV","short_pith_number":"pith:OYXTWZQW","schema_version":"1.0","canonical_sha256":"762f3b66162720dfffd1141b04b3619d472e90708d87dd4ca2c488c7531c697e","source":{"kind":"arxiv","id":"2105.06517","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning Based Safe Decision Making for Highway Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Alan Lynch, Arash Mohammadhasani, Hamed Mehrivash, Zhan Shu","submitted_at":"2021-05-13T19:17:30Z","abstract_excerpt":"In this paper, we develop a safe decision-making method for self-driving cars in a multi-lane, single-agent setting. The proposed approach utilizes deep reinforcement learning (RL) to achieve a high-level policy for safe tactical decision-making. We address two major challenges that arise solely in autonomous navigation. First, the proposed algorithm ensures that collisions never happen, and therefore accelerate the learning process. Second, the proposed algorithm takes into account the unobservable states in the environment. These states appear mainly due to the unpredictable behavior of othe"},"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":"2105.06517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2021-05-13T19:17:30Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"c6f456a060cf43562224d8d9388d0f60894c3cfa5d272f58766335447193c681","abstract_canon_sha256":"f15ce9fd9692a1e71adc949ce389c164cfc80e6601e310f7f6ffbe99a813aa0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:11.284968Z","signature_b64":"67VscGmwRxqIMVKy9mZRWHkUEe/dqAe/p8nph7ptLzlKm/c/iBJynhPNHzLizbgCdEasdVf/Cre3fKa4CO0NDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"762f3b66162720dfffd1141b04b3619d472e90708d87dd4ca2c488c7531c697e","last_reissued_at":"2026-07-05T02:40:11.284520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:11.284520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning Based Safe Decision Making for Highway Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Alan Lynch, Arash Mohammadhasani, Hamed Mehrivash, Zhan Shu","submitted_at":"2021-05-13T19:17:30Z","abstract_excerpt":"In this paper, we develop a safe decision-making method for self-driving cars in a multi-lane, single-agent setting. The proposed approach utilizes deep reinforcement learning (RL) to achieve a high-level policy for safe tactical decision-making. We address two major challenges that arise solely in autonomous navigation. First, the proposed algorithm ensures that collisions never happen, and therefore accelerate the learning process. Second, the proposed algorithm takes into account the unobservable states in the environment. These states appear mainly due to the unpredictable behavior of othe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.06517","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/2105.06517/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":"2105.06517","created_at":"2026-07-05T02:40:11.284586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.06517v1","created_at":"2026-07-05T02:40:11.284586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.06517","created_at":"2026-07-05T02:40:11.284586+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYXTWZQWE4QN","created_at":"2026-07-05T02:40:11.284586+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYXTWZQWE4QN776R","created_at":"2026-07-05T02:40:11.284586+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYXTWZQW","created_at":"2026-07-05T02:40:11.284586+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/OYXTWZQWE4QN776RCQNQJM3BTV","json":"https://pith.science/pith/OYXTWZQWE4QN776RCQNQJM3BTV.json","graph_json":"https://pith.science/api/pith-number/OYXTWZQWE4QN776RCQNQJM3BTV/graph.json","events_json":"https://pith.science/api/pith-number/OYXTWZQWE4QN776RCQNQJM3BTV/events.json","paper":"https://pith.science/paper/OYXTWZQW"},"agent_actions":{"view_html":"https://pith.science/pith/OYXTWZQWE4QN776RCQNQJM3BTV","download_json":"https://pith.science/pith/OYXTWZQWE4QN776RCQNQJM3BTV.json","view_paper":"https://pith.science/paper/OYXTWZQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.06517&json=true","fetch_graph":"https://pith.science/api/pith-number/OYXTWZQWE4QN776RCQNQJM3BTV/graph.json","fetch_events":"https://pith.science/api/pith-number/OYXTWZQWE4QN776RCQNQJM3BTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYXTWZQWE4QN776RCQNQJM3BTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYXTWZQWE4QN776RCQNQJM3BTV/action/storage_attestation","attest_author":"https://pith.science/pith/OYXTWZQWE4QN776RCQNQJM3BTV/action/author_attestation","sign_citation":"https://pith.science/pith/OYXTWZQWE4QN776RCQNQJM3BTV/action/citation_signature","submit_replication":"https://pith.science/pith/OYXTWZQWE4QN776RCQNQJM3BTV/action/replication_record"}},"created_at":"2026-07-05T02:40:11.284586+00:00","updated_at":"2026-07-05T02:40:11.284586+00:00"}