{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:52FYJCSGP5CQWSESUIYUNUBZEY","short_pith_number":"pith:52FYJCSG","schema_version":"1.0","canonical_sha256":"ee8b848a467f450b4892a23146d039261b29c6bb79e00e8ecdc394161bab7dd4","source":{"kind":"arxiv","id":"2207.00244","version":3},"attestation_state":"computed","paper":{"title":"Discriminator-Guided Model-Based Offline Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guyue Zhou, Haoran Xu, Haoyi Niu, Heming Zhang, Ming Li, Peng Cheng, Wenjia Zhang, Xianyuan Zhan","submitted_at":"2022-07-01T07:28:18Z","abstract_excerpt":"Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from severe performance degeneration under limited expert data. Including a learned dynamics model can potentially improve the state-action space coverage of expert data, however, it also faces challenging issues like model approximation/generalization errors and suboptimality of rollout data. In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discri"},"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":"2207.00244","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-01T07:28:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77f2dee98b77d6f6a0d29160f4f0fb916606470cfb6a371b3b02fc78d7aae78c","abstract_canon_sha256":"2de58da67ddc89e3d46c47dd63c756b31e7c56a4400f072bedaab9412f3d01c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:51.180363Z","signature_b64":"TCjEq1pqVOjFQhySk3WGwG7rD+fSaOnm6TUldNxUJhdpF0sNRNYlCT4Pq1tU88bOG7XQ40ghEcfvOQaKyXsXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee8b848a467f450b4892a23146d039261b29c6bb79e00e8ecdc394161bab7dd4","last_reissued_at":"2026-07-05T05:31:51.179875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:51.179875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discriminator-Guided Model-Based Offline Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guyue Zhou, Haoran Xu, Haoyi Niu, Heming Zhang, Ming Li, Peng Cheng, Wenjia Zhang, Xianyuan Zhan","submitted_at":"2022-07-01T07:28:18Z","abstract_excerpt":"Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from severe performance degeneration under limited expert data. Including a learned dynamics model can potentially improve the state-action space coverage of expert data, however, it also faces challenging issues like model approximation/generalization errors and suboptimality of rollout data. In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00244","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/2207.00244/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":"2207.00244","created_at":"2026-07-05T05:31:51.179948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.00244v3","created_at":"2026-07-05T05:31:51.179948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00244","created_at":"2026-07-05T05:31:51.179948+00:00"},{"alias_kind":"pith_short_12","alias_value":"52FYJCSGP5CQ","created_at":"2026-07-05T05:31:51.179948+00:00"},{"alias_kind":"pith_short_16","alias_value":"52FYJCSGP5CQWSES","created_at":"2026-07-05T05:31:51.179948+00:00"},{"alias_kind":"pith_short_8","alias_value":"52FYJCSG","created_at":"2026-07-05T05:31:51.179948+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/52FYJCSGP5CQWSESUIYUNUBZEY","json":"https://pith.science/pith/52FYJCSGP5CQWSESUIYUNUBZEY.json","graph_json":"https://pith.science/api/pith-number/52FYJCSGP5CQWSESUIYUNUBZEY/graph.json","events_json":"https://pith.science/api/pith-number/52FYJCSGP5CQWSESUIYUNUBZEY/events.json","paper":"https://pith.science/paper/52FYJCSG"},"agent_actions":{"view_html":"https://pith.science/pith/52FYJCSGP5CQWSESUIYUNUBZEY","download_json":"https://pith.science/pith/52FYJCSGP5CQWSESUIYUNUBZEY.json","view_paper":"https://pith.science/paper/52FYJCSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.00244&json=true","fetch_graph":"https://pith.science/api/pith-number/52FYJCSGP5CQWSESUIYUNUBZEY/graph.json","fetch_events":"https://pith.science/api/pith-number/52FYJCSGP5CQWSESUIYUNUBZEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52FYJCSGP5CQWSESUIYUNUBZEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52FYJCSGP5CQWSESUIYUNUBZEY/action/storage_attestation","attest_author":"https://pith.science/pith/52FYJCSGP5CQWSESUIYUNUBZEY/action/author_attestation","sign_citation":"https://pith.science/pith/52FYJCSGP5CQWSESUIYUNUBZEY/action/citation_signature","submit_replication":"https://pith.science/pith/52FYJCSGP5CQWSESUIYUNUBZEY/action/replication_record"}},"created_at":"2026-07-05T05:31:51.179948+00:00","updated_at":"2026-07-05T05:31:51.179948+00:00"}