{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MNDM4FE6YI4TQYDAFLM4TDHVJ6","short_pith_number":"pith:MNDM4FE6","schema_version":"1.0","canonical_sha256":"6346ce149ec2393860602ad9c98cf54fb2753d6390f3209e65906d671b800991","source":{"kind":"arxiv","id":"2405.20351","version":3},"attestation_state":"computed","paper":{"title":"Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Jingzehua Xu, Shuai Zhang, Yiyuan Yang, Yubo Huang, Zifeng Zhuang, Ziqi Zhang","submitted_at":"2024-05-28T06:59:16Z","abstract_excerpt":"We propose a novel one-step supervised imitation learning (IL) framework called Adversarial Density Regression (ADR). This IL framework aims to correct the policy learned on unknown-quality to match the expert distribution by utilizing demonstrations, without relying on the Bellman operator. Specifically, ADR addresses several limitations in previous IL algorithms: First, most IL algorithms are based on the Bellman operator, which inevitably suffer from cumulative offsets from sub-optimal rewards during multi-step update processes. Additionally, off-policy training frameworks suffer from Out-o"},"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":"2405.20351","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T06:59:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c44a66331abea76a1d5b0f0ee081c605accbeb38dfa6793509e9e95c1343c43c","abstract_canon_sha256":"229c6bd96c8fa026377a7679401ac60a8e029891333a0dc0cc47aaa3e6517233"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:47.846720Z","signature_b64":"6Lw0DW+eBUUnH6YRHzeiC0er8gsPw1BP8GzsumCb+FqjoRFlmrwCnuy28W/YVGqscsPotqu6ffvBQ9qsdMl7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6346ce149ec2393860602ad9c98cf54fb2753d6390f3209e65906d671b800991","last_reissued_at":"2026-07-05T09:59:47.846232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:47.846232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Jingzehua Xu, Shuai Zhang, Yiyuan Yang, Yubo Huang, Zifeng Zhuang, Ziqi Zhang","submitted_at":"2024-05-28T06:59:16Z","abstract_excerpt":"We propose a novel one-step supervised imitation learning (IL) framework called Adversarial Density Regression (ADR). This IL framework aims to correct the policy learned on unknown-quality to match the expert distribution by utilizing demonstrations, without relying on the Bellman operator. Specifically, ADR addresses several limitations in previous IL algorithms: First, most IL algorithms are based on the Bellman operator, which inevitably suffer from cumulative offsets from sub-optimal rewards during multi-step update processes. Additionally, off-policy training frameworks suffer from Out-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20351","kind":"arxiv","version":3},"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/2405.20351/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":"2405.20351","created_at":"2026-07-05T09:59:47.846293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20351v3","created_at":"2026-07-05T09:59:47.846293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20351","created_at":"2026-07-05T09:59:47.846293+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNDM4FE6YI4T","created_at":"2026-07-05T09:59:47.846293+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNDM4FE6YI4TQYDA","created_at":"2026-07-05T09:59:47.846293+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNDM4FE6","created_at":"2026-07-05T09:59:47.846293+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/MNDM4FE6YI4TQYDAFLM4TDHVJ6","json":"https://pith.science/pith/MNDM4FE6YI4TQYDAFLM4TDHVJ6.json","graph_json":"https://pith.science/api/pith-number/MNDM4FE6YI4TQYDAFLM4TDHVJ6/graph.json","events_json":"https://pith.science/api/pith-number/MNDM4FE6YI4TQYDAFLM4TDHVJ6/events.json","paper":"https://pith.science/paper/MNDM4FE6"},"agent_actions":{"view_html":"https://pith.science/pith/MNDM4FE6YI4TQYDAFLM4TDHVJ6","download_json":"https://pith.science/pith/MNDM4FE6YI4TQYDAFLM4TDHVJ6.json","view_paper":"https://pith.science/paper/MNDM4FE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20351&json=true","fetch_graph":"https://pith.science/api/pith-number/MNDM4FE6YI4TQYDAFLM4TDHVJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/MNDM4FE6YI4TQYDAFLM4TDHVJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNDM4FE6YI4TQYDAFLM4TDHVJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNDM4FE6YI4TQYDAFLM4TDHVJ6/action/storage_attestation","attest_author":"https://pith.science/pith/MNDM4FE6YI4TQYDAFLM4TDHVJ6/action/author_attestation","sign_citation":"https://pith.science/pith/MNDM4FE6YI4TQYDAFLM4TDHVJ6/action/citation_signature","submit_replication":"https://pith.science/pith/MNDM4FE6YI4TQYDAFLM4TDHVJ6/action/replication_record"}},"created_at":"2026-07-05T09:59:47.846293+00:00","updated_at":"2026-07-05T09:59:47.846293+00:00"}