{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JNLVDROM5SGF7Z26K3QNL6IQE4","short_pith_number":"pith:JNLVDROM","schema_version":"1.0","canonical_sha256":"4b5751c5ccec8c5fe75e56e0d5f9102724237167e55ae111f8ef027ccfca3677","source":{"kind":"arxiv","id":"1609.09001","version":2},"attestation_state":"computed","paper":{"title":"Learning from the Hindsight Plan -- Episodic MPC Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Aviv Tamar, Garrett Thomas, Pieter Abbeel, Sergey Levine, Tianhao Zhang","submitted_at":"2016-09-28T16:43:18Z","abstract_excerpt":"Model predictive control (MPC) is a popular control method that has proved effective for robotics, among other fields. MPC performs re-planning at every time step. Re-planning is done with a limited horizon per computational and real-time constraints and often also for robustness to potential model errors. However, the limited horizon leads to suboptimal performance. In this work, we consider the iterative learning setting, where the same task can be repeated several times, and propose a policy improvement scheme for MPC. The main idea is that between executions we can, offline, run MPC with a"},"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":"1609.09001","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-09-28T16:43:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"116639c9508b7aea10ddb9b9902ef0ea9d4b4a6ebfad55021f20c6edf615fa0a","abstract_canon_sha256":"a55d3434b767d4acd7f30d742f421b35deea53f3b977f68ae2b288c631c21a60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:16.952516Z","signature_b64":"LDhcVboKFXSX/ID3qlBNOW9bINchMVPbmV58l5EOtjT3DEWqiYXb0jFIhvPC3jJyJYo61NbVT1wybilbw8nQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b5751c5ccec8c5fe75e56e0d5f9102724237167e55ae111f8ef027ccfca3677","last_reissued_at":"2026-05-18T00:48:16.951839Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:16.951839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from the Hindsight Plan -- Episodic MPC Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Aviv Tamar, Garrett Thomas, Pieter Abbeel, Sergey Levine, Tianhao Zhang","submitted_at":"2016-09-28T16:43:18Z","abstract_excerpt":"Model predictive control (MPC) is a popular control method that has proved effective for robotics, among other fields. MPC performs re-planning at every time step. Re-planning is done with a limited horizon per computational and real-time constraints and often also for robustness to potential model errors. However, the limited horizon leads to suboptimal performance. In this work, we consider the iterative learning setting, where the same task can be repeated several times, and propose a policy improvement scheme for MPC. The main idea is that between executions we can, offline, run MPC with a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.09001","kind":"arxiv","version":2},"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":"1609.09001","created_at":"2026-05-18T00:48:16.951938+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.09001v2","created_at":"2026-05-18T00:48:16.951938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.09001","created_at":"2026-05-18T00:48:16.951938+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNLVDROM5SGF","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNLVDROM5SGF7Z26","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNLVDROM","created_at":"2026-05-18T12:30:25.849896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07238","citing_title":"Leveraging Experience in Lazy Search","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JNLVDROM5SGF7Z26K3QNL6IQE4","json":"https://pith.science/pith/JNLVDROM5SGF7Z26K3QNL6IQE4.json","graph_json":"https://pith.science/api/pith-number/JNLVDROM5SGF7Z26K3QNL6IQE4/graph.json","events_json":"https://pith.science/api/pith-number/JNLVDROM5SGF7Z26K3QNL6IQE4/events.json","paper":"https://pith.science/paper/JNLVDROM"},"agent_actions":{"view_html":"https://pith.science/pith/JNLVDROM5SGF7Z26K3QNL6IQE4","download_json":"https://pith.science/pith/JNLVDROM5SGF7Z26K3QNL6IQE4.json","view_paper":"https://pith.science/paper/JNLVDROM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.09001&json=true","fetch_graph":"https://pith.science/api/pith-number/JNLVDROM5SGF7Z26K3QNL6IQE4/graph.json","fetch_events":"https://pith.science/api/pith-number/JNLVDROM5SGF7Z26K3QNL6IQE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNLVDROM5SGF7Z26K3QNL6IQE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNLVDROM5SGF7Z26K3QNL6IQE4/action/storage_attestation","attest_author":"https://pith.science/pith/JNLVDROM5SGF7Z26K3QNL6IQE4/action/author_attestation","sign_citation":"https://pith.science/pith/JNLVDROM5SGF7Z26K3QNL6IQE4/action/citation_signature","submit_replication":"https://pith.science/pith/JNLVDROM5SGF7Z26K3QNL6IQE4/action/replication_record"}},"created_at":"2026-05-18T00:48:16.951938+00:00","updated_at":"2026-05-18T00:48:16.951938+00:00"}