{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CQ6O6IBW2Y7FLOBVC2RJWABZ4X","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":"59158f32809befbe7978f287debc76b0a53416235f0273793813a1b784c18f7c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-15T04:10:13Z","title_canon_sha256":"42e30e5cba7b6d3d4bf52c9ee0dfc9fae4202d0b3917fabcd2cf72296955ae33"},"schema_version":"1.0","source":{"id":"1908.06012","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.06012","created_at":"2026-07-04T23:57:55Z"},{"alias_kind":"arxiv_version","alias_value":"1908.06012v1","created_at":"2026-07-04T23:57:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06012","created_at":"2026-07-04T23:57:55Z"},{"alias_kind":"pith_short_12","alias_value":"CQ6O6IBW2Y7F","created_at":"2026-07-04T23:57:55Z"},{"alias_kind":"pith_short_16","alias_value":"CQ6O6IBW2Y7FLOBV","created_at":"2026-07-04T23:57:55Z"},{"alias_kind":"pith_short_8","alias_value":"CQ6O6IBW","created_at":"2026-07-04T23:57:55Z"}],"graph_snapshots":[{"event_id":"sha256:e8a092b98782fd9f3cc4d4f981cef4dd519230752c6641b4b46a7b335d796c6c","target":"graph","created_at":"2026-07-04T23:57:55Z","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/1908.06012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jan Peters, Joni Pajarinen, Zhang-Wei Hong","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-15T04:10:13Z","title":"Model-based Lookahead Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06012","kind":"arxiv","version":1},"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":"sha256:12c3335e965a9566d2573b11b8ed4c09db5fe75b72901f8248d2f20d1104d501","target":"record","created_at":"2026-07-04T23:57:55Z","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":"59158f32809befbe7978f287debc76b0a53416235f0273793813a1b784c18f7c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-15T04:10:13Z","title_canon_sha256":"42e30e5cba7b6d3d4bf52c9ee0dfc9fae4202d0b3917fabcd2cf72296955ae33"},"schema_version":"1.0","source":{"id":"1908.06012","kind":"arxiv","version":1}},"canonical_sha256":"143cef2036d63e55b83516a29b0039e5dc022d620d0e4159e1b9ccebf3b87743","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"143cef2036d63e55b83516a29b0039e5dc022d620d0e4159e1b9ccebf3b87743","first_computed_at":"2026-07-04T23:57:55.234362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:57:55.234362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kfYQAnj+BJ1VszUEZMkRyxL9Xv+M3M4D6gXJ3hYB08ceguzyEZ5ltKiQwV+yiu681tkigP8f9p/P1La6uxUVDA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:57:55.234711Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.06012","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12c3335e965a9566d2573b11b8ed4c09db5fe75b72901f8248d2f20d1104d501","sha256:e8a092b98782fd9f3cc4d4f981cef4dd519230752c6641b4b46a7b335d796c6c"],"state_sha256":"4a4027356cd854f213cc1ea68e12c3b4e8295314e5f66ae6e88087e92507669e"}