{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VLNH5BRT7YTKU34FWZUYAZVPLZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b8b2bf4967c2906c5b8ad3257a779393d0433ffd74ce95c75e355710352db385","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T23:52:30Z","title_canon_sha256":"4bcc137cb070b423c20b38f1e49172b29ba4d970e9b40bfe9b07e5e3fec808b7"},"schema_version":"1.0","source":{"id":"1909.11821","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11821","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11821v3","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11821","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"VLNH5BRT7YTK","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"pith_short_16","alias_value":"VLNH5BRT7YTKU34F","created_at":"2026-07-05T00:47:59Z"},{"alias_kind":"pith_short_8","alias_value":"VLNH5BRT","created_at":"2026-07-05T00:47:59Z"}],"graph_snapshots":[{"event_id":"sha256:3a55b28373c7165ae86451a08f3a3a0d035f9689ae74d54660308bc2025b6ef3","target":"graph","created_at":"2026-07-05T00:47:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.11821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hao Su, Peter J. Ramadge, Ting-Han Fan, Yueh-Hua Wu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T23:52:30Z","title":"Model Imitation for Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11821","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:23ef87f2b9e5784314bb65b5a6ae8f2de0c8e1721f9ae3c99b9c6b0aa4428972","target":"record","created_at":"2026-07-05T00:47:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b8b2bf4967c2906c5b8ad3257a779393d0433ffd74ce95c75e355710352db385","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T23:52:30Z","title_canon_sha256":"4bcc137cb070b423c20b38f1e49172b29ba4d970e9b40bfe9b07e5e3fec808b7"},"schema_version":"1.0","source":{"id":"1909.11821","kind":"arxiv","version":3}},"canonical_sha256":"aada7e8633fe26aa6f85b6698066af5e76cc917051bff844899fcd7ee9677935","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aada7e8633fe26aa6f85b6698066af5e76cc917051bff844899fcd7ee9677935","first_computed_at":"2026-07-05T00:47:59.186881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:47:59.186881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4rpLp+P3OzE4KIF8bWjgWEqc9aRMwe6LuxyzuIclJ6dLMYarQrsaEZauKU84Ow7IsEacNXmTgAfTCu8VuYjGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:47:59.187224Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11821","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23ef87f2b9e5784314bb65b5a6ae8f2de0c8e1721f9ae3c99b9c6b0aa4428972","sha256:3a55b28373c7165ae86451a08f3a3a0d035f9689ae74d54660308bc2025b6ef3"],"state_sha256":"b69bc44ed7121a7d875b551f327cfe580961090c84b02f3ec6a19eedfd7a1e60"}