{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VLNH5BRT7YTKU34FWZUYAZVPLZ","short_pith_number":"pith:VLNH5BRT","schema_version":"1.0","canonical_sha256":"aada7e8633fe26aa6f85b6698066af5e76cc917051bff844899fcd7ee9677935","source":{"kind":"arxiv","id":"1909.11821","version":3},"attestation_state":"computed","paper":{"title":"Model Imitation for Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Su, Peter J. Ramadge, Ting-Han Fan, Yueh-Hua Wu","submitted_at":"2019-09-25T23:52:30Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. However, due to estimation error, rollouts in the learned model, especially those of long horizons, fail to match the ones in real-world environments. This mismatching has seriously impacted the sample complexity of MBRL. The phenomenon can be attributed to the fact that previous works employ supervised learning to learn the one-step transition models, which has inherent difficulty ensuring the matching of distributions from multi-step rollouts. Based on th"},"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":"1909.11821","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T23:52:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4bcc137cb070b423c20b38f1e49172b29ba4d970e9b40bfe9b07e5e3fec808b7","abstract_canon_sha256":"b8b2bf4967c2906c5b8ad3257a779393d0433ffd74ce95c75e355710352db385"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:59.187224Z","signature_b64":"4rpLp+P3OzE4KIF8bWjgWEqc9aRMwe6LuxyzuIclJ6dLMYarQrsaEZauKU84Ow7IsEacNXmTgAfTCu8VuYjGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aada7e8633fe26aa6f85b6698066af5e76cc917051bff844899fcd7ee9677935","last_reissued_at":"2026-07-05T00:47:59.186881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:59.186881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Imitation for Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Su, Peter J. Ramadge, Ting-Han Fan, Yueh-Hua Wu","submitted_at":"2019-09-25T23:52:30Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. However, due to estimation error, rollouts in the learned model, especially those of long horizons, fail to match the ones in real-world environments. This mismatching has seriously impacted the sample complexity of MBRL. The phenomenon can be attributed to the fact that previous works employ supervised learning to learn the one-step transition models, which has inherent difficulty ensuring the matching of distributions from multi-step rollouts. Based on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11821","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/1909.11821/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":"1909.11821","created_at":"2026-07-05T00:47:59.186943+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.11821v3","created_at":"2026-07-05T00:47:59.186943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11821","created_at":"2026-07-05T00:47:59.186943+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLNH5BRT7YTK","created_at":"2026-07-05T00:47:59.186943+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLNH5BRT7YTKU34F","created_at":"2026-07-05T00:47:59.186943+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLNH5BRT","created_at":"2026-07-05T00:47:59.186943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09360","citing_title":"D4W: Dependable Data-Driven Dynamics for Wheeled Robots","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLNH5BRT7YTKU34FWZUYAZVPLZ","json":"https://pith.science/pith/VLNH5BRT7YTKU34FWZUYAZVPLZ.json","graph_json":"https://pith.science/api/pith-number/VLNH5BRT7YTKU34FWZUYAZVPLZ/graph.json","events_json":"https://pith.science/api/pith-number/VLNH5BRT7YTKU34FWZUYAZVPLZ/events.json","paper":"https://pith.science/paper/VLNH5BRT"},"agent_actions":{"view_html":"https://pith.science/pith/VLNH5BRT7YTKU34FWZUYAZVPLZ","download_json":"https://pith.science/pith/VLNH5BRT7YTKU34FWZUYAZVPLZ.json","view_paper":"https://pith.science/paper/VLNH5BRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.11821&json=true","fetch_graph":"https://pith.science/api/pith-number/VLNH5BRT7YTKU34FWZUYAZVPLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VLNH5BRT7YTKU34FWZUYAZVPLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLNH5BRT7YTKU34FWZUYAZVPLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLNH5BRT7YTKU34FWZUYAZVPLZ/action/storage_attestation","attest_author":"https://pith.science/pith/VLNH5BRT7YTKU34FWZUYAZVPLZ/action/author_attestation","sign_citation":"https://pith.science/pith/VLNH5BRT7YTKU34FWZUYAZVPLZ/action/citation_signature","submit_replication":"https://pith.science/pith/VLNH5BRT7YTKU34FWZUYAZVPLZ/action/replication_record"}},"created_at":"2026-07-05T00:47:59.186943+00:00","updated_at":"2026-07-05T00:47:59.186943+00:00"}