{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CQ6O6IBW2Y7FLOBVC2RJWABZ4X","short_pith_number":"pith:CQ6O6IBW","schema_version":"1.0","canonical_sha256":"143cef2036d63e55b83516a29b0039e5dc022d620d0e4159e1b9ccebf3b87743","source":{"kind":"arxiv","id":"1908.06012","version":1},"attestation_state":"computed","paper":{"title":"Model-based Lookahead Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jan Peters, Joni Pajarinen, Zhang-Wei Hong","submitted_at":"2019-08-15T04:10:13Z","abstract_excerpt":"Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics. However, despite the impressive data-efficiency, MBRL does not achieve the final performance of state-of-the-art Model-free Reinforcement Learning (MFRL) methods. We leverage the strengths of both realms and propose an approach that obtains high performance with a small amount of data. In particular, we combine MFRL and Model Predictive Control (MPC). While MFRL's strength in exploration allows us to train a better forward dynamics model for MPC, MPC improves "},"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":"1908.06012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-15T04:10:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"42e30e5cba7b6d3d4bf52c9ee0dfc9fae4202d0b3917fabcd2cf72296955ae33","abstract_canon_sha256":"59158f32809befbe7978f287debc76b0a53416235f0273793813a1b784c18f7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:57:55.234711Z","signature_b64":"kfYQAnj+BJ1VszUEZMkRyxL9Xv+M3M4D6gXJ3hYB08ceguzyEZ5ltKiQwV+yiu681tkigP8f9p/P1La6uxUVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"143cef2036d63e55b83516a29b0039e5dc022d620d0e4159e1b9ccebf3b87743","last_reissued_at":"2026-07-04T23:57:55.234362Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:57:55.234362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-based Lookahead Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jan Peters, Joni Pajarinen, Zhang-Wei Hong","submitted_at":"2019-08-15T04:10:13Z","abstract_excerpt":"Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics. However, despite the impressive data-efficiency, MBRL does not achieve the final performance of state-of-the-art Model-free Reinforcement Learning (MFRL) methods. We leverage the strengths of both realms and propose an approach that obtains high performance with a small amount of data. In particular, we combine MFRL and Model Predictive Control (MPC). While MFRL's strength in exploration allows us to train a better forward dynamics model for MPC, MPC improves "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06012","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/1908.06012/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":"1908.06012","created_at":"2026-07-04T23:57:55.234424+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.06012v1","created_at":"2026-07-04T23:57:55.234424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06012","created_at":"2026-07-04T23:57:55.234424+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQ6O6IBW2Y7F","created_at":"2026-07-04T23:57:55.234424+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQ6O6IBW2Y7FLOBV","created_at":"2026-07-04T23:57:55.234424+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQ6O6IBW","created_at":"2026-07-04T23:57:55.234424+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/CQ6O6IBW2Y7FLOBVC2RJWABZ4X","json":"https://pith.science/pith/CQ6O6IBW2Y7FLOBVC2RJWABZ4X.json","graph_json":"https://pith.science/api/pith-number/CQ6O6IBW2Y7FLOBVC2RJWABZ4X/graph.json","events_json":"https://pith.science/api/pith-number/CQ6O6IBW2Y7FLOBVC2RJWABZ4X/events.json","paper":"https://pith.science/paper/CQ6O6IBW"},"agent_actions":{"view_html":"https://pith.science/pith/CQ6O6IBW2Y7FLOBVC2RJWABZ4X","download_json":"https://pith.science/pith/CQ6O6IBW2Y7FLOBVC2RJWABZ4X.json","view_paper":"https://pith.science/paper/CQ6O6IBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.06012&json=true","fetch_graph":"https://pith.science/api/pith-number/CQ6O6IBW2Y7FLOBVC2RJWABZ4X/graph.json","fetch_events":"https://pith.science/api/pith-number/CQ6O6IBW2Y7FLOBVC2RJWABZ4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQ6O6IBW2Y7FLOBVC2RJWABZ4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQ6O6IBW2Y7FLOBVC2RJWABZ4X/action/storage_attestation","attest_author":"https://pith.science/pith/CQ6O6IBW2Y7FLOBVC2RJWABZ4X/action/author_attestation","sign_citation":"https://pith.science/pith/CQ6O6IBW2Y7FLOBVC2RJWABZ4X/action/citation_signature","submit_replication":"https://pith.science/pith/CQ6O6IBW2Y7FLOBVC2RJWABZ4X/action/replication_record"}},"created_at":"2026-07-04T23:57:55.234424+00:00","updated_at":"2026-07-04T23:57:55.234424+00:00"}