{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SYA4FFT2WRXPLCVZ2DRQDA2QMG","short_pith_number":"pith:SYA4FFT2","schema_version":"1.0","canonical_sha256":"9601c2967ab46ef58ab9d0e301835061a8c2136e017df8c07b121f93719ed4b9","source":{"kind":"arxiv","id":"1805.12573","version":5},"attestation_state":"computed","paper":{"title":"Learning a Prior over Intent via Meta-Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anca Dragan, Chelsea Finn, Ellis Ratner, Kelvin Xu, Sergey Levine","submitted_at":"2018-05-31T17:29:25Z","abstract_excerpt":"A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this challenge by instead inferring a reward function from expert behavior. While appealing, it can be impractically expensive to collect datasets of demonstrations that cover the variation common in the real world (e.g. opening any type of door). Thus in practice, IRL must commonly be performed with only a limited set of demonstrations where it can be exceedingly dif"},"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":"1805.12573","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T17:29:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"387c0fc64456f9a8223a00b6533643277731687efed84a6203be132fed7a1d6e","abstract_canon_sha256":"8be6d1e522f71ad4ff5110ed097259b885fb8bad16726d3893fd8deaf85178e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:46.119347Z","signature_b64":"i3pp+gQJC27AFSsiQeu7i652aX8A+ywgBA4apT9Zu2n5jPiVHeDba+2tScmnmhbNXcZb6GY4BHruPDAsAiP1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9601c2967ab46ef58ab9d0e301835061a8c2136e017df8c07b121f93719ed4b9","last_reissued_at":"2026-07-05T00:11:46.118790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:46.118790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Prior over Intent via Meta-Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anca Dragan, Chelsea Finn, Ellis Ratner, Kelvin Xu, Sergey Levine","submitted_at":"2018-05-31T17:29:25Z","abstract_excerpt":"A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this challenge by instead inferring a reward function from expert behavior. While appealing, it can be impractically expensive to collect datasets of demonstrations that cover the variation common in the real world (e.g. opening any type of door). Thus in practice, IRL must commonly be performed with only a limited set of demonstrations where it can be exceedingly dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12573","kind":"arxiv","version":5},"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/1805.12573/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":"1805.12573","created_at":"2026-07-05T00:11:46.118849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.12573v5","created_at":"2026-07-05T00:11:46.118849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12573","created_at":"2026-07-05T00:11:46.118849+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYA4FFT2WRXP","created_at":"2026-07-05T00:11:46.118849+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYA4FFT2WRXPLCVZ","created_at":"2026-07-05T00:11:46.118849+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYA4FFT2","created_at":"2026-07-05T00:11:46.118849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1906.09624","citing_title":"On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17855","citing_title":"QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17855","citing_title":"QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG","json":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG.json","graph_json":"https://pith.science/api/pith-number/SYA4FFT2WRXPLCVZ2DRQDA2QMG/graph.json","events_json":"https://pith.science/api/pith-number/SYA4FFT2WRXPLCVZ2DRQDA2QMG/events.json","paper":"https://pith.science/paper/SYA4FFT2"},"agent_actions":{"view_html":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG","download_json":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG.json","view_paper":"https://pith.science/paper/SYA4FFT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.12573&json=true","fetch_graph":"https://pith.science/api/pith-number/SYA4FFT2WRXPLCVZ2DRQDA2QMG/graph.json","fetch_events":"https://pith.science/api/pith-number/SYA4FFT2WRXPLCVZ2DRQDA2QMG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG/action/storage_attestation","attest_author":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG/action/author_attestation","sign_citation":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG/action/citation_signature","submit_replication":"https://pith.science/pith/SYA4FFT2WRXPLCVZ2DRQDA2QMG/action/replication_record"}},"created_at":"2026-07-05T00:11:46.118849+00:00","updated_at":"2026-07-05T00:11:46.118849+00:00"}