{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YU6J5STR7Q2QFCAJQFYAAMC63P","short_pith_number":"pith:YU6J5STR","schema_version":"1.0","canonical_sha256":"c53c9eca71fc35028809817000305edbff4d9e6aa45e458d7fe366f832cc1ec6","source":{"kind":"arxiv","id":"1903.10077","version":1},"attestation_state":"computed","paper":{"title":"Truly Batch Apprenticeship Learning with Deep Successor Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Donghun Lee, Finale Doshi-Velez, Srivatsan Srinivasan","submitted_at":"2019-03-24T23:13:27Z","abstract_excerpt":"We introduce a novel apprenticeship learning algorithm to learn an expert's underlying reward structure in off-policy model-free \\emph{batch} settings. Unlike existing methods that require a dynamics model or additional data acquisition for on-policy evaluation, our algorithm requires only the batch data of observed expert behavior. Such settings are common in real-world tasks---health care, finance or industrial processes ---where accurate simulators do not exist or data acquisition is costly. To address challenges in batch settings, we introduce Deep Successor Feature Networks(DSFN) that est"},"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":"1903.10077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-24T23:13:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dd8caaf1cdd1aa72cbda436eb1d37c54223242ce593e5b0ba632127bd4b647c3","abstract_canon_sha256":"8beda394f44057b7e4c92a07c3ee159f78e6daac576797dc94f953d5943451d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:32.964621Z","signature_b64":"X8ZCp4D/QRSJBoX5vYKUEehATdq2tPiKKEGR4/M1jDAPdSs9AeSblL9rn4JgyzfCq5au2EiyGIznDxaTnVXuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c53c9eca71fc35028809817000305edbff4d9e6aa45e458d7fe366f832cc1ec6","last_reissued_at":"2026-05-17T23:50:32.964121Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:32.964121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Truly Batch Apprenticeship Learning with Deep Successor Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Donghun Lee, Finale Doshi-Velez, Srivatsan Srinivasan","submitted_at":"2019-03-24T23:13:27Z","abstract_excerpt":"We introduce a novel apprenticeship learning algorithm to learn an expert's underlying reward structure in off-policy model-free \\emph{batch} settings. Unlike existing methods that require a dynamics model or additional data acquisition for on-policy evaluation, our algorithm requires only the batch data of observed expert behavior. Such settings are common in real-world tasks---health care, finance or industrial processes ---where accurate simulators do not exist or data acquisition is costly. To address challenges in batch settings, we introduce Deep Successor Feature Networks(DSFN) that est"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10077","kind":"arxiv","version":1},"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":"1903.10077","created_at":"2026-05-17T23:50:32.964207+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.10077v1","created_at":"2026-05-17T23:50:32.964207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10077","created_at":"2026-05-17T23:50:32.964207+00:00"},{"alias_kind":"pith_short_12","alias_value":"YU6J5STR7Q2Q","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"YU6J5STR7Q2QFCAJ","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"YU6J5STR","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.12831","citing_title":"Quantifying Potential Observation Missingness in Inverse Reinforcement Learning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P","json":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P.json","graph_json":"https://pith.science/api/pith-number/YU6J5STR7Q2QFCAJQFYAAMC63P/graph.json","events_json":"https://pith.science/api/pith-number/YU6J5STR7Q2QFCAJQFYAAMC63P/events.json","paper":"https://pith.science/paper/YU6J5STR"},"agent_actions":{"view_html":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P","download_json":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P.json","view_paper":"https://pith.science/paper/YU6J5STR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.10077&json=true","fetch_graph":"https://pith.science/api/pith-number/YU6J5STR7Q2QFCAJQFYAAMC63P/graph.json","fetch_events":"https://pith.science/api/pith-number/YU6J5STR7Q2QFCAJQFYAAMC63P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P/action/storage_attestation","attest_author":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P/action/author_attestation","sign_citation":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P/action/citation_signature","submit_replication":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P/action/replication_record"}},"created_at":"2026-05-17T23:50:32.964207+00:00","updated_at":"2026-05-17T23:50:32.964207+00:00"}