{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4GA5Q3MK5XORYIMKB3J5BWAXI7","short_pith_number":"pith:4GA5Q3MK","schema_version":"1.0","canonical_sha256":"e181d86d8aeddd1c218a0ed3d0d81747d613b226b75f5eb90021c35822592582","source":{"kind":"arxiv","id":"1902.00778","version":4},"attestation_state":"computed","paper":{"title":"Certified Reinforcement Learning with Logic Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Abate, Daniel Kroening, Hosein Hasanbeig","submitted_at":"2019-02-02T20:09:32Z","abstract_excerpt":"Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to specifying requirements as tasks or goals. We propose a model-free RL algorithm that enables the use of Linear Temporal Logic (LTL) to formulate a goal for unknown continuous-state/action Markov Decision Processes (MDPs). The given LTL property is translated into a Limit-Deterministic Generalised Buchi Automaton (LDGBA), which is then used to shape a synchronous reward "},"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":"1902.00778","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-02T20:09:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"91c206546fb889f69cb26003bf736ee2cac66e2f2975d5304908923b47cd6f51","abstract_canon_sha256":"3bd84eacad7c016a8d01d2e404c291e1532fc9fc0016b25c273932bdd831bf3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:35.082056Z","signature_b64":"vRFrZgRPWs6z+OCtHfqBbUNBArq4l9fabcnja4FTgnHQvjJXu4/IPqVdUuG/lwi40P3v1S8JaR5sB9/AQ2kvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e181d86d8aeddd1c218a0ed3d0d81747d613b226b75f5eb90021c35822592582","last_reissued_at":"2026-07-05T06:17:35.081578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:35.081578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Certified Reinforcement Learning with Logic Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Abate, Daniel Kroening, Hosein Hasanbeig","submitted_at":"2019-02-02T20:09:32Z","abstract_excerpt":"Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to specifying requirements as tasks or goals. We propose a model-free RL algorithm that enables the use of Linear Temporal Logic (LTL) to formulate a goal for unknown continuous-state/action Markov Decision Processes (MDPs). The given LTL property is translated into a Limit-Deterministic Generalised Buchi Automaton (LDGBA), which is then used to shape a synchronous reward "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00778","kind":"arxiv","version":4},"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/1902.00778/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":"1902.00778","created_at":"2026-07-05T06:17:35.081634+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00778v4","created_at":"2026-07-05T06:17:35.081634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00778","created_at":"2026-07-05T06:17:35.081634+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GA5Q3MK5XOR","created_at":"2026-07-05T06:17:35.081634+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GA5Q3MK5XORYIMK","created_at":"2026-07-05T06:17:35.081634+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GA5Q3MK","created_at":"2026-07-05T06:17:35.081634+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/4GA5Q3MK5XORYIMKB3J5BWAXI7","json":"https://pith.science/pith/4GA5Q3MK5XORYIMKB3J5BWAXI7.json","graph_json":"https://pith.science/api/pith-number/4GA5Q3MK5XORYIMKB3J5BWAXI7/graph.json","events_json":"https://pith.science/api/pith-number/4GA5Q3MK5XORYIMKB3J5BWAXI7/events.json","paper":"https://pith.science/paper/4GA5Q3MK"},"agent_actions":{"view_html":"https://pith.science/pith/4GA5Q3MK5XORYIMKB3J5BWAXI7","download_json":"https://pith.science/pith/4GA5Q3MK5XORYIMKB3J5BWAXI7.json","view_paper":"https://pith.science/paper/4GA5Q3MK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00778&json=true","fetch_graph":"https://pith.science/api/pith-number/4GA5Q3MK5XORYIMKB3J5BWAXI7/graph.json","fetch_events":"https://pith.science/api/pith-number/4GA5Q3MK5XORYIMKB3J5BWAXI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GA5Q3MK5XORYIMKB3J5BWAXI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GA5Q3MK5XORYIMKB3J5BWAXI7/action/storage_attestation","attest_author":"https://pith.science/pith/4GA5Q3MK5XORYIMKB3J5BWAXI7/action/author_attestation","sign_citation":"https://pith.science/pith/4GA5Q3MK5XORYIMKB3J5BWAXI7/action/citation_signature","submit_replication":"https://pith.science/pith/4GA5Q3MK5XORYIMKB3J5BWAXI7/action/replication_record"}},"created_at":"2026-07-05T06:17:35.081634+00:00","updated_at":"2026-07-05T06:17:35.081634+00:00"}