{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SGMQAHDOMBP4QXMPNJR3SEHV6P","short_pith_number":"pith:SGMQAHDO","schema_version":"1.0","canonical_sha256":"9199001c6e605fc85d8f6a63b910f5f3ee1041eeeaf2420679b6ab2bd0ddaa72","source":{"kind":"arxiv","id":"1901.02161","version":2},"attestation_state":"computed","paper":{"title":"Risk-Aware Active Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel S. Brown, Scott Niekum, Yuchen Cui","submitted_at":"2019-01-08T05:23:03Z","abstract_excerpt":"Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. Utilizing recent advances in performance bounds for inverse reinforcement learning, we propose a risk-aware active inverse reinforcement learning algorithm that focuses active queries on areas of the state space with the potential for large generalization error. We show that risk-"},"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":"1901.02161","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T05:23:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"382e845386cfe09ad512bbecd8fe66950035988a2e51695bda22c7f886e70b2e","abstract_canon_sha256":"339bf88315cbeea7a666f5405c47d9f4f67c31c87bcdd0b16fbed8d2c9e19581"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:21.861939Z","signature_b64":"4AIabSFFxSlEtzQjBb3uX08yXZgYYKwNa77hnz03JR6nbU2Y/EhgKJdjj6yPmfM+IpA2n5vxTiuiN86Hor36CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9199001c6e605fc85d8f6a63b910f5f3ee1041eeeaf2420679b6ab2bd0ddaa72","last_reissued_at":"2026-05-17T23:44:21.861219Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:21.861219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk-Aware Active Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel S. Brown, Scott Niekum, Yuchen Cui","submitted_at":"2019-01-08T05:23:03Z","abstract_excerpt":"Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. Utilizing recent advances in performance bounds for inverse reinforcement learning, we propose a risk-aware active inverse reinforcement learning algorithm that focuses active queries on areas of the state space with the potential for large generalization error. We show that risk-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02161","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":"1901.02161","created_at":"2026-05-17T23:44:21.861339+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.02161v2","created_at":"2026-05-17T23:44:21.861339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02161","created_at":"2026-05-17T23:44:21.861339+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGMQAHDOMBP4","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGMQAHDOMBP4QXMP","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGMQAHDO","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.08928","citing_title":"Learning Reward Functions by Integrating Human Demonstrations and Preferences","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1906.10099","citing_title":"DynoPlan: Combining Motion Planning and Deep Neural Network based Controllers for Safe HRL","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGMQAHDOMBP4QXMPNJR3SEHV6P","json":"https://pith.science/pith/SGMQAHDOMBP4QXMPNJR3SEHV6P.json","graph_json":"https://pith.science/api/pith-number/SGMQAHDOMBP4QXMPNJR3SEHV6P/graph.json","events_json":"https://pith.science/api/pith-number/SGMQAHDOMBP4QXMPNJR3SEHV6P/events.json","paper":"https://pith.science/paper/SGMQAHDO"},"agent_actions":{"view_html":"https://pith.science/pith/SGMQAHDOMBP4QXMPNJR3SEHV6P","download_json":"https://pith.science/pith/SGMQAHDOMBP4QXMPNJR3SEHV6P.json","view_paper":"https://pith.science/paper/SGMQAHDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.02161&json=true","fetch_graph":"https://pith.science/api/pith-number/SGMQAHDOMBP4QXMPNJR3SEHV6P/graph.json","fetch_events":"https://pith.science/api/pith-number/SGMQAHDOMBP4QXMPNJR3SEHV6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGMQAHDOMBP4QXMPNJR3SEHV6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGMQAHDOMBP4QXMPNJR3SEHV6P/action/storage_attestation","attest_author":"https://pith.science/pith/SGMQAHDOMBP4QXMPNJR3SEHV6P/action/author_attestation","sign_citation":"https://pith.science/pith/SGMQAHDOMBP4QXMPNJR3SEHV6P/action/citation_signature","submit_replication":"https://pith.science/pith/SGMQAHDOMBP4QXMPNJR3SEHV6P/action/replication_record"}},"created_at":"2026-05-17T23:44:21.861339+00:00","updated_at":"2026-05-17T23:44:21.861339+00:00"}