{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VHNP4VIHAGTUDNMJDFKCZSZRBX","short_pith_number":"pith:VHNP4VIH","schema_version":"1.0","canonical_sha256":"a9dafe550701a741b58919542ccb310df323394858f6cd56a8579314f776a5a5","source":{"kind":"arxiv","id":"1810.08926","version":4},"attestation_state":"computed","paper":{"title":"Teaching Inverse Reinforcement Learners via Features and Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adish Singla, Luis Haug, Sebastian Tschiatschek","submitted_at":"2018-10-21T10:44:22Z","abstract_excerpt":"Learning near-optimal behaviour from an expert's demonstrations typically relies on the assumption that the learner knows the features that the true reward function depends on. In this paper, we study the problem of learning from demonstrations in the setting where this is not the case, i.e., where there is a mismatch between the worldviews of the learner and the expert. We introduce a natural quantity, the teaching risk, which measures the potential suboptimality of policies that look optimal to the learner in this setting. We show that bounds on the teaching risk guarantee that the learner i"},"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":"1810.08926","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-21T10:44:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"878abadf3bcdc285d8b3c046b9e9e2cb8d927a3b6a941f71d7a7650df380b3e2","abstract_canon_sha256":"261f6bee409bcda07018101ca4431d5cc706e3c8b8e448ad7a2878a3812a488f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:06.866009Z","signature_b64":"wmyBWYDD9oCk4OYGjYF8zJKp9xf50Og/X16FG+s6kCCQlEWiP0TRBwqRU//4SqlURh6t+Ok/zVl4oVsKQdrXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9dafe550701a741b58919542ccb310df323394858f6cd56a8579314f776a5a5","last_reissued_at":"2026-05-17T23:50:06.865503Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:06.865503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teaching Inverse Reinforcement Learners via Features and Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adish Singla, Luis Haug, Sebastian Tschiatschek","submitted_at":"2018-10-21T10:44:22Z","abstract_excerpt":"Learning near-optimal behaviour from an expert's demonstrations typically relies on the assumption that the learner knows the features that the true reward function depends on. In this paper, we study the problem of learning from demonstrations in the setting where this is not the case, i.e., where there is a mismatch between the worldviews of the learner and the expert. We introduce a natural quantity, the teaching risk, which measures the potential suboptimality of policies that look optimal to the learner in this setting. We show that bounds on the teaching risk guarantee that the learner i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08926","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":"1810.08926","created_at":"2026-05-17T23:50:06.865587+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.08926v4","created_at":"2026-05-17T23:50:06.865587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08926","created_at":"2026-05-17T23:50:06.865587+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHNP4VIHAGTU","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHNP4VIHAGTUDNMJ","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHNP4VIH","created_at":"2026-05-18T12:32:59.047623+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/VHNP4VIHAGTUDNMJDFKCZSZRBX","json":"https://pith.science/pith/VHNP4VIHAGTUDNMJDFKCZSZRBX.json","graph_json":"https://pith.science/api/pith-number/VHNP4VIHAGTUDNMJDFKCZSZRBX/graph.json","events_json":"https://pith.science/api/pith-number/VHNP4VIHAGTUDNMJDFKCZSZRBX/events.json","paper":"https://pith.science/paper/VHNP4VIH"},"agent_actions":{"view_html":"https://pith.science/pith/VHNP4VIHAGTUDNMJDFKCZSZRBX","download_json":"https://pith.science/pith/VHNP4VIHAGTUDNMJDFKCZSZRBX.json","view_paper":"https://pith.science/paper/VHNP4VIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.08926&json=true","fetch_graph":"https://pith.science/api/pith-number/VHNP4VIHAGTUDNMJDFKCZSZRBX/graph.json","fetch_events":"https://pith.science/api/pith-number/VHNP4VIHAGTUDNMJDFKCZSZRBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHNP4VIHAGTUDNMJDFKCZSZRBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHNP4VIHAGTUDNMJDFKCZSZRBX/action/storage_attestation","attest_author":"https://pith.science/pith/VHNP4VIHAGTUDNMJDFKCZSZRBX/action/author_attestation","sign_citation":"https://pith.science/pith/VHNP4VIHAGTUDNMJDFKCZSZRBX/action/citation_signature","submit_replication":"https://pith.science/pith/VHNP4VIHAGTUDNMJDFKCZSZRBX/action/replication_record"}},"created_at":"2026-05-17T23:50:06.865587+00:00","updated_at":"2026-05-17T23:50:06.865587+00:00"}