{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LP7XIXLIUGNOKJ6EORBQH2I3V5","short_pith_number":"pith:LP7XIXLI","schema_version":"1.0","canonical_sha256":"5bff745d68a19ae527c4744303e91baf5a63c8e6342b57f5089fe707764d5241","source":{"kind":"arxiv","id":"2305.03360","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Offline Model-Based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Haoyang He","submitted_at":"2023-05-05T08:23:56Z","abstract_excerpt":"Model-based approaches are becoming increasingly popular in the field of offline reinforcement learning, with high potential in real-world applications due to the model's capability of thoroughly utilizing the large historical datasets available with supervised learning techniques. This paper presents a literature review of recent work in offline model-based reinforcement learning, a field that utilizes model-based approaches in offline reinforcement learning. The survey provides a brief overview of the concepts and recent developments in both offline reinforcement learning and model-based rei"},"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":"2305.03360","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-05T08:23:56Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"96b613790a536060dbde7aeb76057b7bcd5077221bac5c8bfe9634fe3694e6eb","abstract_canon_sha256":"90dbd8493943fffeaf5e38feab86400beaa7a89eb219243744d17b11c0375597"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:22.444395Z","signature_b64":"I45mCvJZ4beY0n1xHQjSmmugTIN1LNw136PvfCYGFP2D5DH69UiS5WpBDs5/3QwVfK75OU+R3ADLXQDfBcicCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bff745d68a19ae527c4744303e91baf5a63c8e6342b57f5089fe707764d5241","last_reissued_at":"2026-07-05T06:07:22.444003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:22.444003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Offline Model-Based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Haoyang He","submitted_at":"2023-05-05T08:23:56Z","abstract_excerpt":"Model-based approaches are becoming increasingly popular in the field of offline reinforcement learning, with high potential in real-world applications due to the model's capability of thoroughly utilizing the large historical datasets available with supervised learning techniques. This paper presents a literature review of recent work in offline model-based reinforcement learning, a field that utilizes model-based approaches in offline reinforcement learning. The survey provides a brief overview of the concepts and recent developments in both offline reinforcement learning and model-based rei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03360","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.03360/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":"2305.03360","created_at":"2026-07-05T06:07:22.444059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.03360v1","created_at":"2026-07-05T06:07:22.444059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03360","created_at":"2026-07-05T06:07:22.444059+00:00"},{"alias_kind":"pith_short_12","alias_value":"LP7XIXLIUGNO","created_at":"2026-07-05T06:07:22.444059+00:00"},{"alias_kind":"pith_short_16","alias_value":"LP7XIXLIUGNOKJ6E","created_at":"2026-07-05T06:07:22.444059+00:00"},{"alias_kind":"pith_short_8","alias_value":"LP7XIXLI","created_at":"2026-07-05T06:07:22.444059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05735","citing_title":"Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5","json":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5.json","graph_json":"https://pith.science/api/pith-number/LP7XIXLIUGNOKJ6EORBQH2I3V5/graph.json","events_json":"https://pith.science/api/pith-number/LP7XIXLIUGNOKJ6EORBQH2I3V5/events.json","paper":"https://pith.science/paper/LP7XIXLI"},"agent_actions":{"view_html":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5","download_json":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5.json","view_paper":"https://pith.science/paper/LP7XIXLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.03360&json=true","fetch_graph":"https://pith.science/api/pith-number/LP7XIXLIUGNOKJ6EORBQH2I3V5/graph.json","fetch_events":"https://pith.science/api/pith-number/LP7XIXLIUGNOKJ6EORBQH2I3V5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5/action/storage_attestation","attest_author":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5/action/author_attestation","sign_citation":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5/action/citation_signature","submit_replication":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5/action/replication_record"}},"created_at":"2026-07-05T06:07:22.444059+00:00","updated_at":"2026-07-05T06:07:22.444059+00:00"}