{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4JPUBWXIQQATWSURVXXVGXEIN7","short_pith_number":"pith:4JPUBWXI","schema_version":"1.0","canonical_sha256":"e25f40dae884013b4a91adef535c886fd9de09b6ebc48ee9d19018ad45c0bdd1","source":{"kind":"arxiv","id":"1904.07189","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Alireza Nakhaei, Jana Tumova, Jesper Karlsson, Kikuo Fujimura, Maxime Bouton, Mykel J. Kochenderfer","submitted_at":"2019-04-15T17:03:35Z","abstract_excerpt":"Designing reliable decision strategies for autonomous urban driving is challenging. Reinforcement learning (RL) has been used to automatically derive suitable behavior in uncertain environments, but it does not provide any guarantee on the performance of the resulting policy. We propose a generic approach to enforce probabilistic guarantees on an RL agent. An exploration strategy is derived prior to training that constrains the agent to choose among actions that satisfy a desired probabilistic specification expressed with linear temporal logic (LTL). Reducing the search space to policies satis"},"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":"1904.07189","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-04-15T17:03:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2a495a5cb068ac56a484d0925d8af98717a1183fa28669904394f6ee27b778f","abstract_canon_sha256":"df71ea398b92f1d9f1ff4db6170541ae46ddaf6a5c12ffc6e5b40907e0442800"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:42.273950Z","signature_b64":"JeqRh/X4OpJF2B5BLMBinWFzmgnLijYNZRG8+p/sH+x59MTq/77kJNGL9bInXXm0kKcIOzWj6nk9gw7Lo1cIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e25f40dae884013b4a91adef535c886fd9de09b6ebc48ee9d19018ad45c0bdd1","last_reissued_at":"2026-05-17T23:44:42.273404Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:42.273404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Alireza Nakhaei, Jana Tumova, Jesper Karlsson, Kikuo Fujimura, Maxime Bouton, Mykel J. Kochenderfer","submitted_at":"2019-04-15T17:03:35Z","abstract_excerpt":"Designing reliable decision strategies for autonomous urban driving is challenging. Reinforcement learning (RL) has been used to automatically derive suitable behavior in uncertain environments, but it does not provide any guarantee on the performance of the resulting policy. We propose a generic approach to enforce probabilistic guarantees on an RL agent. An exploration strategy is derived prior to training that constrains the agent to choose among actions that satisfy a desired probabilistic specification expressed with linear temporal logic (LTL). Reducing the search space to policies satis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.07189","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":""},"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":"1904.07189","created_at":"2026-05-17T23:44:42.273504+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.07189v2","created_at":"2026-05-17T23:44:42.273504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.07189","created_at":"2026-05-17T23:44:42.273504+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JPUBWXIQQAT","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JPUBWXIQQATWSUR","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JPUBWXI","created_at":"2026-05-18T12:33:10.108867+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/4JPUBWXIQQATWSURVXXVGXEIN7","json":"https://pith.science/pith/4JPUBWXIQQATWSURVXXVGXEIN7.json","graph_json":"https://pith.science/api/pith-number/4JPUBWXIQQATWSURVXXVGXEIN7/graph.json","events_json":"https://pith.science/api/pith-number/4JPUBWXIQQATWSURVXXVGXEIN7/events.json","paper":"https://pith.science/paper/4JPUBWXI"},"agent_actions":{"view_html":"https://pith.science/pith/4JPUBWXIQQATWSURVXXVGXEIN7","download_json":"https://pith.science/pith/4JPUBWXIQQATWSURVXXVGXEIN7.json","view_paper":"https://pith.science/paper/4JPUBWXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.07189&json=true","fetch_graph":"https://pith.science/api/pith-number/4JPUBWXIQQATWSURVXXVGXEIN7/graph.json","fetch_events":"https://pith.science/api/pith-number/4JPUBWXIQQATWSURVXXVGXEIN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JPUBWXIQQATWSURVXXVGXEIN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JPUBWXIQQATWSURVXXVGXEIN7/action/storage_attestation","attest_author":"https://pith.science/pith/4JPUBWXIQQATWSURVXXVGXEIN7/action/author_attestation","sign_citation":"https://pith.science/pith/4JPUBWXIQQATWSURVXXVGXEIN7/action/citation_signature","submit_replication":"https://pith.science/pith/4JPUBWXIQQATWSURVXXVGXEIN7/action/replication_record"}},"created_at":"2026-05-17T23:44:42.273504+00:00","updated_at":"2026-05-17T23:44:42.273504+00:00"}