{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YF75QKFC2IGSXV7GM2SVLNINZ2","short_pith_number":"pith:YF75QKFC","schema_version":"1.0","canonical_sha256":"c17fd828a2d20d2bd7e666a555b50dce9ba726313f5ea9252c8d889bccfc75e8","source":{"kind":"arxiv","id":"1703.03078","version":3},"attestation_state":"computed","paper":{"title":"Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gaurav Sukhatme, Karol Hausman, Marvin Zhang, Sergey Levine, Stefan Schaal, Yevgen Chebotar","submitted_at":"2017-03-08T23:58:56Z","abstract_excerpt":"Reinforcement learning (RL) algorithms for real-world robotic applications need a data-efficient learning process and the ability to handle complex, unknown dynamical systems. These requirements are handled well by model-based and model-free RL approaches, respectively. In this work, we aim to combine the advantages of these two types of methods in a principled manner. By focusing on time-varying linear-Gaussian policies, we enable a model-based algorithm based on the linear quadratic regulator (LQR) that can be integrated into the model-free framework of path integral policy improvement (PI2)"},"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":"1703.03078","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-08T23:58:56Z","cross_cats_sorted":[],"title_canon_sha256":"46df40cff9d6e3e758d9fa486df171f328d15b3bd378d372678b1672c1bcd886","abstract_canon_sha256":"5beb01bd66090a9e32de1433dcc09a7cbf004a46c87d1d77aaadde94be5e05df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:12.291247Z","signature_b64":"/oeUioETu8AbVhlOCXgFPD2tuSX/CifE3B2qVABIYP8tPiS6wV4u720L0Vws9HfutbXlX9IWY6lM9+N50hE8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c17fd828a2d20d2bd7e666a555b50dce9ba726313f5ea9252c8d889bccfc75e8","last_reissued_at":"2026-05-18T00:42:12.290665Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:12.290665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gaurav Sukhatme, Karol Hausman, Marvin Zhang, Sergey Levine, Stefan Schaal, Yevgen Chebotar","submitted_at":"2017-03-08T23:58:56Z","abstract_excerpt":"Reinforcement learning (RL) algorithms for real-world robotic applications need a data-efficient learning process and the ability to handle complex, unknown dynamical systems. These requirements are handled well by model-based and model-free RL approaches, respectively. In this work, we aim to combine the advantages of these two types of methods in a principled manner. By focusing on time-varying linear-Gaussian policies, we enable a model-based algorithm based on the linear quadratic regulator (LQR) that can be integrated into the model-free framework of path integral policy improvement (PI2)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03078","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":""},"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":"1703.03078","created_at":"2026-05-18T00:42:12.290742+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.03078v3","created_at":"2026-05-18T00:42:12.290742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03078","created_at":"2026-05-18T00:42:12.290742+00:00"},{"alias_kind":"pith_short_12","alias_value":"YF75QKFC2IGS","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"YF75QKFC2IGSXV7G","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"YF75QKFC","created_at":"2026-05-18T12:31:56.362134+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/YF75QKFC2IGSXV7GM2SVLNINZ2","json":"https://pith.science/pith/YF75QKFC2IGSXV7GM2SVLNINZ2.json","graph_json":"https://pith.science/api/pith-number/YF75QKFC2IGSXV7GM2SVLNINZ2/graph.json","events_json":"https://pith.science/api/pith-number/YF75QKFC2IGSXV7GM2SVLNINZ2/events.json","paper":"https://pith.science/paper/YF75QKFC"},"agent_actions":{"view_html":"https://pith.science/pith/YF75QKFC2IGSXV7GM2SVLNINZ2","download_json":"https://pith.science/pith/YF75QKFC2IGSXV7GM2SVLNINZ2.json","view_paper":"https://pith.science/paper/YF75QKFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.03078&json=true","fetch_graph":"https://pith.science/api/pith-number/YF75QKFC2IGSXV7GM2SVLNINZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/YF75QKFC2IGSXV7GM2SVLNINZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YF75QKFC2IGSXV7GM2SVLNINZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YF75QKFC2IGSXV7GM2SVLNINZ2/action/storage_attestation","attest_author":"https://pith.science/pith/YF75QKFC2IGSXV7GM2SVLNINZ2/action/author_attestation","sign_citation":"https://pith.science/pith/YF75QKFC2IGSXV7GM2SVLNINZ2/action/citation_signature","submit_replication":"https://pith.science/pith/YF75QKFC2IGSXV7GM2SVLNINZ2/action/replication_record"}},"created_at":"2026-05-18T00:42:12.290742+00:00","updated_at":"2026-05-18T00:42:12.290742+00:00"}