{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NMLS6CKA6AUVE35LFGOFPSZ6JZ","short_pith_number":"pith:NMLS6CKA","schema_version":"1.0","canonical_sha256":"6b172f0940f029526fab299c57cb3e4e6e0b6a7c08772af12f18358be26365b4","source":{"kind":"arxiv","id":"1710.07983","version":4},"attestation_state":"computed","paper":{"title":"Safety-Aware Apprenticeship Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Weichao Zhou, Wenchao Li","submitted_at":"2017-10-22T17:29:16Z","abstract_excerpt":"Apprenticeship learning (AL) is a kind of Learning from Demonstration techniques where the reward function of a Markov Decision Process (MDP) is unknown to the learning agent and the agent has to derive a good policy by observing an expert's demonstrations. In this paper, we study the problem of how to make AL algorithms inherently safe while still meeting its learning objective. We consider a setting where the unknown reward function is assumed to be a linear combination of a set of state features, and the safety property is specified in Probabilistic Computation Tree Logic (PCTL). By embeddi"},"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":"1710.07983","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-22T17:29:16Z","cross_cats_sorted":[],"title_canon_sha256":"a173f80045d3be7fe587c38a1d234cd40366adc17476a0dae338a32bd83d97f9","abstract_canon_sha256":"a86728c30929fa2b86806fe155e173c152e451ad1297fd7375994e3ca522ac60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:19.036623Z","signature_b64":"v4D8JqRieedgFukmsXyRIZ+P7Y+IJFpgyLjpDjycynFoCChBSRYfEivYXBAeCfX7X+joZnZLdHYMDb/cuby1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b172f0940f029526fab299c57cb3e4e6e0b6a7c08772af12f18358be26365b4","last_reissued_at":"2026-05-18T00:17:19.036158Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:19.036158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safety-Aware Apprenticeship Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Weichao Zhou, Wenchao Li","submitted_at":"2017-10-22T17:29:16Z","abstract_excerpt":"Apprenticeship learning (AL) is a kind of Learning from Demonstration techniques where the reward function of a Markov Decision Process (MDP) is unknown to the learning agent and the agent has to derive a good policy by observing an expert's demonstrations. In this paper, we study the problem of how to make AL algorithms inherently safe while still meeting its learning objective. We consider a setting where the unknown reward function is assumed to be a linear combination of a set of state features, and the safety property is specified in Probabilistic Computation Tree Logic (PCTL). By embeddi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.07983","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":""},"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":"1710.07983","created_at":"2026-05-18T00:17:19.036230+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.07983v4","created_at":"2026-05-18T00:17:19.036230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.07983","created_at":"2026-05-18T00:17:19.036230+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMLS6CKA6AUV","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMLS6CKA6AUVE35L","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMLS6CKA","created_at":"2026-05-18T12:31:34.259226+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/NMLS6CKA6AUVE35LFGOFPSZ6JZ","json":"https://pith.science/pith/NMLS6CKA6AUVE35LFGOFPSZ6JZ.json","graph_json":"https://pith.science/api/pith-number/NMLS6CKA6AUVE35LFGOFPSZ6JZ/graph.json","events_json":"https://pith.science/api/pith-number/NMLS6CKA6AUVE35LFGOFPSZ6JZ/events.json","paper":"https://pith.science/paper/NMLS6CKA"},"agent_actions":{"view_html":"https://pith.science/pith/NMLS6CKA6AUVE35LFGOFPSZ6JZ","download_json":"https://pith.science/pith/NMLS6CKA6AUVE35LFGOFPSZ6JZ.json","view_paper":"https://pith.science/paper/NMLS6CKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.07983&json=true","fetch_graph":"https://pith.science/api/pith-number/NMLS6CKA6AUVE35LFGOFPSZ6JZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NMLS6CKA6AUVE35LFGOFPSZ6JZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMLS6CKA6AUVE35LFGOFPSZ6JZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMLS6CKA6AUVE35LFGOFPSZ6JZ/action/storage_attestation","attest_author":"https://pith.science/pith/NMLS6CKA6AUVE35LFGOFPSZ6JZ/action/author_attestation","sign_citation":"https://pith.science/pith/NMLS6CKA6AUVE35LFGOFPSZ6JZ/action/citation_signature","submit_replication":"https://pith.science/pith/NMLS6CKA6AUVE35LFGOFPSZ6JZ/action/replication_record"}},"created_at":"2026-05-18T00:17:19.036230+00:00","updated_at":"2026-05-18T00:17:19.036230+00:00"}