{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ARMB6D3HFKFQTWNYOVHIFZEE26","short_pith_number":"pith:ARMB6D3H","schema_version":"1.0","canonical_sha256":"04581f0f672a8b09d9b8754e82e484d79ef81fd517b2451f16ef5adc9945769e","source":{"kind":"arxiv","id":"1812.03565","version":2},"attestation_state":"computed","paper":{"title":"The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Recht, Stephen Tu","submitted_at":"2018-12-09T22:24:26Z","abstract_excerpt":"The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL). Motivated by recent empirical success of RL on continuous control tasks, we study the sample complexity of popular model-based and model-free algorithms on the Linear Quadratic Regulator (LQR). We show that for policy evaluation, a simple model-based plugin method requires asymptotically less samples than the classical least-squares temporal difference (LSTD) estimator to reach the same quality of solution; the sample complexity gap between the two methods can be at least a fa"},"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":"1812.03565","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-09T22:24:26Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a70ddebb8694a1bd8c721519f6d30fcdf4c4f927ba33631f3de172301b0a60dd","abstract_canon_sha256":"d6c59c48f2d9fcb0044300e90b00a139709821abf516bd1bcccf429e51fa5540"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:53.299533Z","signature_b64":"l2+mL22ctSPuRvOls0Wwv3ixv7wRF6CeKX6HpQ1+BhH+8G1ytBg7Fb5ScwuQJmxyjjFQDwqYOjO1t+YwMTNWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04581f0f672a8b09d9b8754e82e484d79ef81fd517b2451f16ef5adc9945769e","last_reissued_at":"2026-05-17T23:54:53.299030Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:53.299030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Recht, Stephen Tu","submitted_at":"2018-12-09T22:24:26Z","abstract_excerpt":"The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL). Motivated by recent empirical success of RL on continuous control tasks, we study the sample complexity of popular model-based and model-free algorithms on the Linear Quadratic Regulator (LQR). We show that for policy evaluation, a simple model-based plugin method requires asymptotically less samples than the classical least-squares temporal difference (LSTD) estimator to reach the same quality of solution; the sample complexity gap between the two methods can be at least a fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03565","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":"1812.03565","created_at":"2026-05-17T23:54:53.299101+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.03565v2","created_at":"2026-05-17T23:54:53.299101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03565","created_at":"2026-05-17T23:54:53.299101+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARMB6D3HFKFQ","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARMB6D3HFKFQTWNY","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARMB6D3H","created_at":"2026-05-18T12:32:13.499390+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/ARMB6D3HFKFQTWNYOVHIFZEE26","json":"https://pith.science/pith/ARMB6D3HFKFQTWNYOVHIFZEE26.json","graph_json":"https://pith.science/api/pith-number/ARMB6D3HFKFQTWNYOVHIFZEE26/graph.json","events_json":"https://pith.science/api/pith-number/ARMB6D3HFKFQTWNYOVHIFZEE26/events.json","paper":"https://pith.science/paper/ARMB6D3H"},"agent_actions":{"view_html":"https://pith.science/pith/ARMB6D3HFKFQTWNYOVHIFZEE26","download_json":"https://pith.science/pith/ARMB6D3HFKFQTWNYOVHIFZEE26.json","view_paper":"https://pith.science/paper/ARMB6D3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.03565&json=true","fetch_graph":"https://pith.science/api/pith-number/ARMB6D3HFKFQTWNYOVHIFZEE26/graph.json","fetch_events":"https://pith.science/api/pith-number/ARMB6D3HFKFQTWNYOVHIFZEE26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARMB6D3HFKFQTWNYOVHIFZEE26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARMB6D3HFKFQTWNYOVHIFZEE26/action/storage_attestation","attest_author":"https://pith.science/pith/ARMB6D3HFKFQTWNYOVHIFZEE26/action/author_attestation","sign_citation":"https://pith.science/pith/ARMB6D3HFKFQTWNYOVHIFZEE26/action/citation_signature","submit_replication":"https://pith.science/pith/ARMB6D3HFKFQTWNYOVHIFZEE26/action/replication_record"}},"created_at":"2026-05-17T23:54:53.299101+00:00","updated_at":"2026-05-17T23:54:53.299101+00:00"}