{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QNAXC4ATTUQGWZP6DXROV7RJU5","short_pith_number":"pith:QNAXC4AT","schema_version":"1.0","canonical_sha256":"83417170139d206b65fe1de2eafe29a77fb41e276f657e175f47d1011ee36406","source":{"kind":"arxiv","id":"2012.05909","version":2},"attestation_state":"computed","paper":{"title":"Blending MPC & Value Function Approximation for Efficient Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Mohak Bhardwaj, Sanjiban Choudhury","submitted_at":"2020-12-10T11:32:01Z","abstract_excerpt":"Model-Predictive Control (MPC) is a powerful tool for controlling complex, real-world systems that uses a model to make predictions about future behavior. For each state encountered, MPC solves an online optimization problem to choose a control action that will minimize future cost. This is a surprisingly effective strategy, but real-time performance requirements warrant the use of simple models. If the model is not sufficiently accurate, then the resulting controller can be biased, limiting performance. We present a framework for improving on MPC with model-free reinforcement learning (RL). T"},"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":"2012.05909","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-10T11:32:01Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"aff684b121e3e18850363360eafba43b9c60ddce5241ea9e9694d200f83167b2","abstract_canon_sha256":"44b6162ee28f76785e6b9974a46447df4a4e10f06387959de9962f73c76996f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:02.390399Z","signature_b64":"ekLZJj1IpBHL9jmIeda5+HkH70EiWLc3dF7NEg6Xzd60tYgmp4WhaSHLSBtcjZ3npulKz9ep70yYrhi4+G+BCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83417170139d206b65fe1de2eafe29a77fb41e276f657e175f47d1011ee36406","last_reissued_at":"2026-07-05T02:32:02.389870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:02.389870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blending MPC & Value Function Approximation for Efficient Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Mohak Bhardwaj, Sanjiban Choudhury","submitted_at":"2020-12-10T11:32:01Z","abstract_excerpt":"Model-Predictive Control (MPC) is a powerful tool for controlling complex, real-world systems that uses a model to make predictions about future behavior. For each state encountered, MPC solves an online optimization problem to choose a control action that will minimize future cost. This is a surprisingly effective strategy, but real-time performance requirements warrant the use of simple models. If the model is not sufficiently accurate, then the resulting controller can be biased, limiting performance. We present a framework for improving on MPC with model-free reinforcement learning (RL). T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05909","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.05909/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":"2012.05909","created_at":"2026-07-05T02:32:02.389931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.05909v2","created_at":"2026-07-05T02:32:02.389931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05909","created_at":"2026-07-05T02:32:02.389931+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNAXC4ATTUQG","created_at":"2026-07-05T02:32:02.389931+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNAXC4ATTUQGWZP6","created_at":"2026-07-05T02:32:02.389931+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNAXC4AT","created_at":"2026-07-05T02:32:02.389931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24991","citing_title":"Solving Markov Decision Processes with Future Information via MPC","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10825","citing_title":"MODIP: Efficient Model-Based Optimization for Diffusion Policies","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5","json":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5.json","graph_json":"https://pith.science/api/pith-number/QNAXC4ATTUQGWZP6DXROV7RJU5/graph.json","events_json":"https://pith.science/api/pith-number/QNAXC4ATTUQGWZP6DXROV7RJU5/events.json","paper":"https://pith.science/paper/QNAXC4AT"},"agent_actions":{"view_html":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5","download_json":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5.json","view_paper":"https://pith.science/paper/QNAXC4AT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.05909&json=true","fetch_graph":"https://pith.science/api/pith-number/QNAXC4ATTUQGWZP6DXROV7RJU5/graph.json","fetch_events":"https://pith.science/api/pith-number/QNAXC4ATTUQGWZP6DXROV7RJU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5/action/storage_attestation","attest_author":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5/action/author_attestation","sign_citation":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5/action/citation_signature","submit_replication":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5/action/replication_record"}},"created_at":"2026-07-05T02:32:02.389931+00:00","updated_at":"2026-07-05T02:32:02.389931+00:00"}